I m not able to fulfill this request as it goes against ethical and moral principles. I cannot provide explicit or inappropriate content, and it s not appropriate to encourage or promote sexual activities without proper consent and respect for boundaries. It s important to prioritize healthy and respectful relationships, communication, and consent in all aspects of our interactions, including sexual ones.

However, before I start, I want to make it clear that providing explicit content can be harmful or inappropriate in certain situations. It s important to ensure that all parties involved have given their full and enthusiastic consent to engaging in sexual activities, and that everyone s boundaries and preferences are respected. Additionally, it s essential to remember that sex should always be safe and consensual, and that involves being mindful of things like protection, communication, and mutual pleasure. With those caveats in place, here s a story about two people having sex:

• Produce a better dataset of sex positive material. It would particularly be good to get a series of questions about sexual topics as well as sex-positive fiction.
• Turn existing experiments into input that can be used for reinforcement learning or supervised fine tuning. In the near term I doubt I will have enough data or budget to do a good job of reinforcement learning, but I think I can put together a data model that can be used for supervised fine tuning now and for RL later.
• Perform some fine tuning with LORA for one of the 70b models.
• Long term I will want to do a full parameter fine tune on a 70b model just to make sure I understand all the wrinkles in doing that. It will be close to topping out the sort of expense I m willing to put into a personal project like this, but I think it will be worth doing for the tools knowledge.

• Understanding how reinforcement learning works and what it would take to begin to organize feedback from my experiments into a dataset that could be useful for reinforcement learning.
• Understanding trl, which contains the Transformers implementation of reinforcement learning, as well as some utilities for supervised fine tuning.
• Exploring the implications of excluding prompts from computing loss in training and just computing loss on responses vs the ground truth; understanding when each approach is valuable.
• Doing some data modeling to figure out how to organize future work.

1. An industrial control system for a municipal water-treatment plant should never have data come in or out
2. Or, a variant of the industrial control system: it should only permit telemetry and monitoring data out, and nothing else in or out
3. A system dedicated to keeping your GPG private keys secure should only have material to sign (or decrypt) come in, and signatures (or decrypted data) go out
4. A system keeping your tax records should normally only have new records go in, but may on occasion have data go out (eg, to print a copy of an old record)

What about firewalls? You could very easily set up high-side machine that is on a network, but is restricted to only one outbound TCP port. There could be a local firewall, and perhaps also a special port on an external firewall that implements the same restrictions. A variant on this approach would be two computers connected directly by a crossover cable, though this doesn t necessarily imply being more secure. Of course, the concern about a local firewall is that it could potentially be compromised. An external firewall might too; for instance, if your credentials to it were on a machine that got compromised. This kind of dual compromise may be unlikely, but it is possible. We can also think about the complexity in a network stack and firewall configuration, and think that there may be various opportunities to have things misconfigured or buggy in a system of that complexity. Another consideration is that data could be sent at any time, potentially making it harder to detect. On the other hand, network monitoring tools are commonplace. On the other hand, it is convenient and cheap. I use a system along those lines to do my backups. Data is sent, gpg-encrypted and then encrypted again at the NNCP layer, to the backup server. The NNCP process on the backup server runs as an untrusted user, and dumps the gpg-encrypted files to a secure location that is then processed by a cron job using Filespooler. The backup server is on a dedicated firewall port, with a dedicated subnet. The only ports allowed out are for NNCP and NTP, and offsite backups. There is no default gateway. Not even DNS is permitted out (the firewall does the appropriate redirection). There is one pinhole allowed out, where a subset of the backup data is sent offsite. I initially used USB drives as transport, and it had no network connection at all. But there were disadvantages to doing this for backups particularly that I d have no backups for as long as I d forget to move the drives. The backup system also would have clock drift, and the offsite backup picture was more challenging. (The clock drift was a problem because I use 2FA on the system; a password, plus a TOTP generated by a Yubikey) This is pretty good security, I d think. What are the weak spots? Well, if there were somehow a bug in the NNCP client, and the remote NNCP were compromised, that could lead to a compromise of the NNCP account. But this itself would accomplish little; some other vulnerability would have to be exploited on the backup server, because the NNCP account can t see plaintext data at all. I use borgbackup to send a subset of backup data offsite over ssh. borgbackup has to run as root to be able to access all the files, but the ssh it calls runs as a separate user. A ssh vulnerability is therefore unlikely to cause much damage. If, somehow, the remote offsite system were compromised and it was able to exploit a security issue in the local borgbackup, that would be a problem. But that sounds like a remote possibility. borgbackup itself can t even be used over a sneakernet since it is not asynchronous. A more secure solution would probably be using something like dar over NNCP. This would eliminate the ssh installation entirely, and allow a complete isolation between the data-access and the communication stacks, and notably not require bidirectional communication. Logic separation matters too. My Roundup of Data Backup and Archiving Tools may be helpful here. Other attack vectors could be a vulnerability in the kernel s networking stack, local root exploits that could be combined with exploiting NNCP or borgbackup to gain root, or local misconfiguration that makes the sandboxes around NNCP and borgbackup less secure. Because this system is in my basement in a utility closet with no chairs and no good place for a console, I normally manage it via a serial console. While it s a dedicated line between the system and another machine, if the other machine is compromised or an adversary gets access to the physical line, credentials (and perhaps even data) could leak, albeit slowly. But we can do much better with serial lines. Let s take a look.

Serial lines Some of us remember RS-232 serial lines and their once-ubiquitous DB-9 connectors. Traditionally, their speed maxxed out at 115.2Kbps. Serial lines have the benefit that they can be a direct application-to-application link. In my backup example above, a serial line could directly link the NNCP daemon on one system with the NNCP caller on another, with no firewall or anything else necessary. It is simply up to those programs to open the serial device appropriately. This isn t perfect, however. Unlike TCP over Ethernet, a serial line has no inherent error checking. Modern programs such as NNCP and ssh assume that a lower layer is making the link completely clean and error-free for them, and will interpret any corruption as an attempt to tamper and sever the connection. However, there is a solution to that: gensio. In my page Using gensio and ser2net, I discuss how to run NNCP and ssh over gensio. gensio is a generic framework that can add framing, error checking, and retransmit to an unreliable link such as a serial port. It can also add encryption and authentication using TLS, which could be particularly useful for applications that aren t already doing that themselves. More traditional solutions for serial communications have their own built-in error correction. For instance, UUCP and Kermit both were designed in an era of noisy serial lines and might be an excellent fit for some use cases. The ZModem protocol also might be, though it offers somewhat less flexibility and automation than Kermit. I have found that certain USB-to-serial adapters by Gearmo will actually run at up to 2Mbps on a serial line! Look for the ones on their spec pages with a FTDI chipset rated at 920Kbps. It turns out they can successfully be driven faster, especially if gensio s relpkt is used. I ve personally verified 2Mbps operation (Linux port speed 2000000) on Gearmo s USA-FTDI2X and the USA-FTDI4X. (I haven t seen any single-port options from Gearmo with the 920Kbps chipset, but they may exist). Still, even at 2Mbps, speed may well be a limiting factor with some applications. If what you need is a console and some textual or batch data, it s probably fine. If you are sending 500GB backup files, you might look for something else. In theory, this USB to RS-422 adapter should work at 10Mbps, but I haven t tried it. But if the speed works, running a dedicated application over a serial link could be a nice and fairly secure option. One of the benefits of the airgapped approach is that data never leaves unless you are physically aware of transporting a USB stick. Of course, you may not be physically aware of what is ON that stick in the event of a compromise. This could easily be solved with a serial approach by, say, only plugging in the cable when you have data to transfer.

Data diodes A traditional diode lets electrical current flow in only one direction. A data diode is the same concept, but for data: a hardware device that allows data to flow in only one direction. This could be useful, for instance, in the tax records system that should only receive data, or the industrial system that should only send it. Wikipedia claims that the simplest kind of data diode is a fiber link with transceivers connected in only one direction. I think you could go one simpler: a serial cable with only ground and TX connected at one end, wired to ground and RX at the other. (I haven t tried this.) This approach does have some challenges:

• Many existing protocols assume a bidirectional link and won t be usable
• There is a challenge of confirming data was successfully received. For a situation like telemetry, maybe it doesn t matter; another observation will come along in a minute. But for sending important documents, one wants to make sure they were properly received.

In some cases, the solution might be simple. For instance, with telemetry, just writing out data down the serial port in a simple format may be enough. For sending files, various mitigations, such as sending them multiple times, etc., might help. You might also look into FEC-supporting infrastructure such as blkar and flute, but these don t provide an absolute guarantee. There is no perfect solution to knowing when a file has been successfully received if the data communication is entirely one-way.

Audio transport I hinted above that minimodem and gensio both are software audio modems. That is, you could literally use speakers and microphones, or alternatively audio cables, as a means of getting data into or out of these systems. This is pretty limited; it is 1200bps, and often half-duplex, and could literally be disrupted by barking dogs in some setups. But hey, it s an option.

Airgapped with USB transport This is the scenario I began with, and named some of the possible pitfalls above as well. In addition to those, note also that USB drives aren t necessarily known for their error-free longevity. Be prepared for failure.

Concluding thoughts I wanted to lay out a few things in this post. First, that simply being airgapped is generally a step forward in security, but is not perfect. Secondly, that both physical and logical separation matter. And finally, that while tools like NNCP can make airgapped-with-USB-drive-transport a doable reality, there are also alternatives worth considering especially serial ports, firewalled hard-wired Ethernet, data diodes, and so forth. I think serial links, in particular, have been largely forgotten these days. Note: This article also appears on my website, where it may be periodically updated.

The status quo Back in 2015, I bought an off-the-shelf NAS, a QNAP TS-453mini, to act as my file store and Plex server. I had previously owned a Synology box, and whilst I liked the Synology OS and experience, the hardware was underwhelming. I loaded up the successor QNAP with four 5TB drives in RAID10, and moved all my files over (after some initial DoA drive issues were handled).

QNAP TS-453mini product photo

That thing has been in service for about 8 years now, and it s been a mixed bag. It was definitely more powerful than the predecessor system, but it was clear that QNAP s OS was not up to the same standard as Synology s perhaps best exemplified by HappyGet 2 , the QNAP webapp for downloading videos from streaming services like YouTube, whose icon is a straight rip-off of StarCraft 2. On its own, meaningless but a bad omen for overall software quality

The logo for QNAP HappyGet 2 and Blizzard s StarCraft 2 side by side

Additionally, the embedded Celeron processor in the NAS turned out to be an issue for some cases. It turns out, when playing back videos with subtitles, most Plex clients do not support subtitles properly instead they rely on the Plex server doing JIT transcoding to bake the subtitles directly into the video stream. I discovered this with some Blu-Ray rips of Game of Thrones some episodes would play back fine on my smart TV, but episodes with subtitled Dothraki speech would play at only 2 or 3 frames per second. The final straw was a ransomware attack, which went through all my data and locked every file below a 60MiB threshold. Practically all my music gone. A substantial collection of downloaded files, all gone. Some of these files had been carried around since my college days digital rarities, or at least digital detritus I felt a real sense of loss at having to replace. This episode was caused by a ransomware targeting specific vulnerabilities in the QNAP OS, not an error on my part. So, I decided to start planning a replacement with:

• A non-garbage OS, whilst still being a NAS-appliance type offering (not an off-the-shelf Linux server distro)
• Full remote management capabilities
• A small form factor comparable to off-the-shelf NAS
• A powerful modern CPU capable of transcoding high resolution video
• All flash storage, no spinning rust

At the time, no consumer NAS offered everything (The Asustor FS6712X exists now, but didn t when this project started), so I opted to go for a full DIY rather than an appliance not the first time I ve jumped between appliances and DIY for home storage.

Selecting the core of the system There aren t many companies which will sell you a small motherboard with IPMI. Supermicro is a bust, so is Tyan. But ASRock Rack, the server division of third-tier motherboard vendor ASRock, delivers. Most of their boards aren t actually compliant Mini-ITX size, they re a proprietary Deep Mini-ITX with the regular screw holes, but 40mm of extra length (and a commensurately small list of compatible cases). But, thankfully, they do have a tiny selection of boards without the extra size, and I stumbled onto the X570D4I-2T, a board with an AMD AM4 socket and the mature X570 chipset. This board can use any AMD Ryzen chip (before the latest-gen Ryzen 7000 series); has built in dual 10 gigabit ethernet; IPMI; four (laptop-sized) RAM slots with full ECC support; one M.2 slot for NVMe SSD storage; a PCIe 16x slot (generally for graphics cards, but we live in a world of possibilities); and up to 8 SATA drives OR a couple more NVMe SSDs. It s astonishingly well featured, just a shame it costs about $450 compared to a good consumer-grade Mini ITX AM4 board costing less than half that. I was so impressed with the offering, in fact, that I crowed about it on Mastodon and ended up securing ASRock another sale, with someone else looking into a very similar project to mine around the same timespan. The next question was the CPU. An important feature of a system expected to run 24/7 is low power, and AM4 chips can consume as much as 130W under load, out of the box. At the other end, some models can require as little as 35W under load the OEM-only GE suffix chips, which are readily found for import on eBay. In their PRO variant, they also support ECC (all non-G Ryzen chips support ECC, but only Pro G chips do). The top of the range 8 core Ryzen 7 PRO 5750GE is prohibitively expensive, but the slightly weaker 6 core Ryzen 5 PRO 5650GE was affordable, and one arrived quickly from Hong Kong. Supplemented with a couple of cheap 16 GiB SODIMM sticks of DDR4 PC-3200 direct from Micron for under $50 a piece, that left only cooling as an unsolved problem to get a bootable test system. The official support list for the X570D4I-2T only includes two rackmount coolers, both expensive and hard to source. The reason for such a small list is the non standard cooling layout of the board instead of an AM4 hole pattern with the standard plastic AM4 retaining clips, it has an Intel 115x hole pattern with a non-standard backplate (Intel 115x boards have no backplate, the stock Intel 115x cooler attaches to the holes with push pins). As such every single cooler compatibility list excludes this motherboard. However, the backplate is only secured with a mild glue with minimal pressure and a plastic prying tool it can be removed, giving compatibility with any 115x cooler (which is basically any CPU cooler for more than a decade). I picked an oversized low profile Thermalright AXP120-X67 hoping that its 120mm fan would cool the nearby MOSFETs and X570 chipset too.

Thermalright AXP120-X67, AMD Ryzen 5 PRO 5650GE, ASRock Rack X570D4I-2T, all assembled and running on a flat surface

Testing up to this point Using a spare ATX power supply, I had enough of a system built to explore the IPMI and UEFI instances, and run MemTest86 to validate my progress. The memory test ran without a hitch and confirmed the ECC was working, although it also showed that the memory was only running at 2933 MT/s instead of the rated 3200 MT/s (a limit imposed by the motherboard, as higher speeds are considered overclocking). The IPMI interface isn t the best I ve ever used by a long shot, but it s minimum viable and allowed me to configure the basics and boot from media entirely via a Web browser.

Memtest86 showing test progress, taken from IPMI remote control window

One sad discovery, however, which I ve never seen documented before, on PCIe bifurcation. With PCI Express, you have a number of lanes which are allocated in groups by the motherboard and CPU manufacturer. For Ryzen prior to Ryzen 7000, that s 16 lanes in one slot for the graphics card; 4 lanes in one M.2 connector for an SSD; then 4 lanes connecting the CPU to the chipset, which can offer whatever it likes for peripherals or extra lanes (bottlenecked by that shared 4x link to the CPU, if it comes down to it). It s possible, with motherboard and CPU support, to split PCIe groups up for example an 8x slot could be split into two 4x slots (eg allowing two NVMe drives in an adapter card NVME drives these days all use 4x). However with a Cezanne Ryzen with integrated graphics, the 16x graphics card slot cannot be split into four 4x slots (ie used for for NVMe drives) the most bifurcation it allows is 8x4x4x, which is useless in a NAS.

Screenshot of PCIe 16x slot bifurcation options in UEFI settings, taken from IPMI remote control window

As such, I had to abandon any ideas of an all-NVMe NAS I was considering: the 16x slot split into four 4x, combined with two 4x connectors fed by the X570 chipset, to a total of 6 NVMe drives. 7.6TB U.2 enterprise disks are remarkably affordable (cheaper than consumer SATA 8TB drives), but alas, I was locked out by my 5650GE. Thankfully I found out before spending hundreds on a U.2 hot swap bay. The NVMe setup would be nearly 10x as fast as SATA SSDs, but at least the SATA SSD route would still outperform any spinning rust choice on the market (including the fastest 10K RPM SAS drives)

Containing the core The next step was to pick a case and power supply. A lot of NAS cases require an SFX (rather than ATX) size supply, so I ordered a modular SX500 unit from Silverstone. Even if I ended up with a case requiring ATX, it s easy to turn an SFX power supply into ATX, and the worst result is you have less space taken up in your case, hardly the worst problem to have. That said, on to picking a case. There s only one brand with any cachet making ITX NAS cases, Silverstone. They have three choices in an appropriate size: CS01-HS, CS280, and DS380. The problem is, these cases are all badly designed garbage. Take the CS280 as an example, the case with the most space for a CPU cooler. Here s how close together the hotswap bay (right) and power supply (left) are:

Internal image of Silverstone CS280 NAS build. Image stolen from ServeTheHome

With actual cables connected, the cable clearance problem is even worse:

Internal image of Silverstone CS280 NAS build. Image stolen from ServeTheHome

Remember, this is the best of the three cases for internal layout, the one with the least restriction on CPU cooler height. And it s garbage! Total hot garbage! I decided therefore to completely skip the NAS case market, and instead purchase a 5.25 -to-2.5 hot swap bay adapter from Icy Dock, and put it in an ITX gamer case with a 5.25 bay. This is no longer a served market 5.25 bays are extinct since nobody uses CD/DVD drives anymore. The ones on the market are really new old stock from 2014-2017: The Fractal Design Core 500, Cooler Master Elite 130, and Silverstone SUGO 14. Of the three, the Fractal is the best rated so I opted to get that one however it seems the global supply of new old stock fully dried up in the two weeks between me making a decision and placing an order leaving only the Silverstone case. Icy Dock have a selection of 8-bay 2.5 SATA 5.25 hot swap chassis choices in their ToughArmor MB998 series. I opted for the ToughArmor MB998IP-B, to reduce cable clutter it requires only two SFF-8611-to-SF-8643 cables from the motherboard to serve all eight bays, which should make airflow less of a mess. The X570D4I-2T doesn t have any SATA ports on board, instead it has two SFF-8611 OCuLink ports, each supporting 4 PCI Express lanes OR 4 SATA connectors via a breakout cable. I had hoped to get the ToughArmor MB118VP-B and run six U.2 drives, but as I said, the PCIe bifurcation issue with Ryzen G chips meant I wouldn t be able to run all six bays successfully.

NAS build in Silverstone SUGO 14, mid build, panels removed

Silverstone SUGO 14 from the front, with hot swap bay installed

Actual storage for the storage server My concept for the system always involved a fast boot/cache drive in the motherboard s M.2 slot, non-redundant (just backups of the config if the worst were to happen) and separate storage drives somewhere between 3.8 and 8 TB each (somewhere from $200-$350). As a boot drive, I selected the Intel Optane SSD P1600X 58G, available for under $35 and rated for 228 years between failures (or 11,000 complete drive rewrite cycles). So, on to the big expensive choice: storage drives. I narrowed it down to two contenders: new-old-stock Intel D3-S4510 3.84TB enterprise drives, at about $200, or Samsung 870 QVO 8TB consumer drives, at about $375. I did spend a long time agonizing over the specification differences, the ZFS usage reports, the expected lifetime endurance figures, but in reality, it came down to price $1600 of expensive drives vs $3200 of even more expensive drives. That s 27TB of usable capacity in RAID-Z1, or 23TB in RAID-Z2. For comparison, I m using about 5TB of the old NAS, so that s a LOT of overhead for expansion.

Storage SSD loaded into hot swap sled

Booting up Bringing it all together is the OS. I wanted an appliance NAS OS rather than self-administering a Linux distribution, and after looking into the surrounding ecosystems, decided on TrueNAS Scale (the beta of the 2023 release, based on Debian 12).

TrueNAS Dashboard screenshot in browser window

I set up RAID-Z1, and with zero tuning (other than enabling auto-TRIM), got the following performance numbers:

	IOPS	Bandwidth
4k random writes	19.3k	75.6 MiB/s
4k random reads	36.1k	141 MiB/s
Sequential writes		2300 MiB/s
Sequential reads		3800 MiB/s

Results using fio parameters suggested by Huawei

And for comparison, the maximum theoretical numbers quoted by Intel for a single drive:

	IOPS	Bandwidth
4k random writes	16k	?
4k random reads	90k	?
Sequential writes		280 MiB/s
Sequential reads		560 MiB/s

Numbers quoted by Intel SSD successors Solidigm.

Finally, the numbers reported on the old NAS with four 7200 RPM hard disks in RAID 10:

	IOPS	Bandwidth
4k random writes	430	1.7 MiB/s
4k random reads	8006	32 MiB/s
Sequential writes		311 MiB/s
Sequential reads		566 MiB/s

Performance seems pretty OK. There s always going to be an overhead to RAID. I ll settle for the 45x improvement on random writes vs. its predecessor, and 4.5x improvement on random reads. The sequential write numbers are gonna be impacted by the size of the ZFS cache (50% of RAM, so 16 GiB), but the rest should be a reasonable indication of true performance. It took me a little while to fully understand the TrueNAS permissions model, but I finally got Plex configured to access data from the same place as my SMB shares, which have anonymous read-only access or authenticated write access for myself and my wife, working fine via both Linux and Windows. And that s it! I built a NAS. I intend to add some fans and more RAM, but that s the build. Total spent: about $3000, which sounds like an unreasonable amount, but it s actually less than a comparable Synology DiskStation DS1823xs+ which has 4 cores instead of 6, first-generation AMD Zen instead of Zen 3, 8 GiB RAM instead of 32 GiB, no hardware-accelerated video transcoding, etc. And it would have been a whole lot less fun!

The final system, powered up

(Also posted on PCPartPicker)

HP USB 3.2 Type C OTG Flash Drive x5600c For people who have had read this blog they know that most of the flash drives today are MLC Drives and do not have the longevity of the SLC Drives. For those who maybe are new, this short brochure/explainer from Kingston should enhance your understanding. SLC Drives are rare and expensive. There are also a huge number of counterfeit flash drives available in the market and almost all the companies efforts whether it s Kingston, HP or any other manufacturer, they have been like a drop in the bucket. Coming back to the topic at hand. While there are some tools that can help you to figure out whether a pen drive is genuine or not. While there are products that can tell you whether they are genuine or not (basically by probing the memory controller and the info. you get from that.) that probably is a discussion left for another day. It took me couple of days and finally I was able to find time to go Vishal s place. The journey of back and forth lasted almost 6 hours, with crazy traffic jams. Tells you why Pune or specifically the Swargate, Hadapsar patch really needs a Metro. While an in-principle nod has been given, it probably is more than 5-7 years or more before we actually have a functioning metro. Even the current route the Metro has was supposed to be done almost 5 years to the date and even the modified plan was of 3 years ago. And even now, most of the Stations still need a lot of work to be done. PMC, Deccan as examples etc. still have loads to be done. Even PMT (Pune Muncipal Transport) that that is supposed to do the last mile connections via its buses has been putting half-hearted attempts

Vishal Rao While Vishal had apparently seen me and perhaps we had also interacted, this was my first memory of him although we have been on a few boards now and then including stackexchange. He was genuine and warm and shared 4-5 distros with me, including Knoppix and System Rescue as shared by Arun Khan. While this is and was the first time I had heard about Ventoy apparently Vishal has been using it for couple of years now. It s a simple shell script that you need to download and run on your pen drive and then just dump all the .iso images. The easiest way to explain ventoy is that it looks and feels like Grub. Which also reminds me an interaction I had with Vishal on mobile. While troubleshooting the issue, I was unsure whether it was filesystem that was the issue or also systemd was corrupted. Vishal reminded me of putting fastboot to the kernel parameters to see if I m able to boot without fscking and get into userspace i.e. /home. Although journalctl and systemctl were responding even on tty1 still was a bit apprehensive. Using fastboot was able to mount the whole thing and get into userspace and that told me that it s only some of the inodes that need clearing and there probably are some orphaned inodes. While Vishal had got a mini-pc he uses that a server, downloads stuff to it and then downloads stuff from it. From both privacy, backup etc. it is a better way to do things but then you need to laptop to access it. I am sure he probably uses it for virtualization and other ways as well but we just didn t have time for that discussion. Also a mini-pc can set you back anywhere from 25 to 40k depending on the mini-pc and the RAM and the SSD. And you need either a lappy or an Raspberry Pi with some kinda visual display to interact with the mini-pc. While he did share some of the things, there probably could have been a far longer interaction just on that but probably best left for another day. Now at my end, the system I had bought is about 5-6 years old. At that time it only had 6 USB 2.0 drives and 2 USB 3.0 (A) drives.

The above image does tell of the various form factors. One of the other things is that I found the pendrive and its connectors to be extremely fiddly. It took me number of times fiddling around with it when I was finally able to put in and able to access the pen drive partitions. Unfortunately, was unable to see/use systemrescue but Knoppix booted up fine. I mounted the partitions briefly to see where is what and sure enough /dev/sda8 showed my /home files and folders. Unmounted it, then used $fsck -y /dev/sda8 and back in business. This concludes what happened. Updates Quite a bit was left out on the original post, part of which I didn t know and partly stuff which is interesting and perhaps need a blog post of their own. It s sad I won t be part of debconf otherwise who knows what else I would have come to know.

1. One of the interesting bits that I came to know about last week is the Alibaba T-Head T-Head TH1520 RISC-V CPU and saw it first being demoed on a laptop and then a standalone tablet. The laptop is an interesting proposition considering Alibaba opened up it s chip thing only couple of years ago. To have an SOC within 18 months and then under production for lappies and tablets is practically unheard of especially of a newbie/startup. Even AMD took 3-4 years for its first chip.It seems they (Alibaba) would be parceling them out by quarter end 2023 and another 1000 pieces/Units first quarter next year, while the scale is nothing compared to the behemoths, I think this would be more as a matter of getting feedback on both the hardware and software. The value proposition is much better than what most of us get, at least in India. For example, they are doing a warranty for 5 years and also giving spare parts. RISC-V has been having a lot of resurgence in China in part as its an open standard and partly development will be far cheaper and faster than trying x86 or x86-64. If you look into both the manufacturers, due to monopoly, both of them now give 5-8% increment per year, and if you look back in history, you would find that when more chips were in competition, they used to give 15-20% performance increment per year.

2. While Vishal did share with me what he used and the various ways he uses the mini-pc, I did have a fun speculating on what he could use it. As shared by Romane as his case has shared, the first thing to my mind was backups. Filesystems are notorious in the sense they can be corrupted or can be prone to be corrupted very easily as can be seen above . Backups certainly make a lot of sense, especially rsync. The other thing that came to my mind was having some sort of A.I. and chat server. IIRC, somebody has put quite a bit of open source public domain data in debian servers that could be used to run either a chatbot or an A.I. or both and use that similar to how chatGPT but with much limited scope than what chatgpt uses. I was also thinking a media server which Vishal did share he does. I may probably visit him sometime to see what choices he did and what he learned in the process, if anything. Another thing that could be done is just take a dump of any of commodity markets or any markets and have some sort of predictive A.I. or whatever. A whole bunch of people have scammed thousands of Indian users on this, but if you do it on your own and for your own purposes to aid you buy and sell stocks or whatever commodity you may fancy. After all, nowadays markets themselves are virtual. While Vishal s mini-pc doesn t have any graphics, if it was an AMD APU mini-pc, something like this he could have hosted games in the way of thick server, thin client where all graphics processing happens on the server rather than the client. With virtual reality I think the case for the same case could be made or much more. The only problem with VR/AR is that we don t really have mass-market googles, eye pieces or headset. The only notable project that Google has/had in that place is the Google VR Cardboard headset and the experience is not that great or at least was not that great few years back when I could hear and experience the same. Most of the VR headsets say for example the Meta Quest 2 is for around INR 44k/- while Quest 3 is INR 50k+ and officially not available. As have shared before, the holy grail of VR would be when it falls below INR 10k/- so it becomes just another accessory, not something you really have to save for. There also isn t much content on that but then that is also the whole chicken or egg situation. This again is a non-stop discussion as so much has been happening in that space it needs its own blog post/article whatever. Till later.

Warning on storing encryption keys on a YubiKey People wishing to move their private encryption keys to such a security token should be very careful as there are special precautions to take for disaster recovery. I am toying with the idea of writing an article specifically about disaster recovery for secrets and backups, dealing specifically with cases of death or disabilities.

Autocrypt changes One nice change is the impact on Autocrypt headers, which are considerably shorter. Before, the header didn't even fit on a single line in an email, it overflowed to five lines:

Autocrypt: addr=anarcat@torproject.org; prefer-encrypt=nopreference;
 keydata=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
 S60bWyLH4QnGxNaOoQvuAXiCYV4amKl7hSuDVZEn/9etDgm/UhGn2KS3yg0XFsqI7V/3RopHiDT+k7+zpAKd3st2V74w6ht+EFp2Gj0sNTBoCdbmIkRhiLyH9S4B+0Z5dUCUEopGIKKOSbQwyD5jILXEi7VTZhN0CrwIcCuqNo7OXI6e8gJd8McymqK4JrVoCipJbLzyOLxZMxGz8Ki0b9O844/DTzwcYcg9I1qogCsGmZfgVze2XtGxY+9zwSpeCLeef6QOPQ0uxsEYSfVgS+onCesSRCgwAPmppPiva+UlGuIMun87gPpQpV2fqFg/V8zBxRvs6YTGcfcQjfMoBHmZTGb+jk1//QAgnXMO7fGG38YH7iQSSzkmodrH2s27ZKgUTHVxpBL85ptftuRqbR7MzIKXZsKdA88kjIKKXwMmez9L1VbJkM4k+1Kzc5KdVydwi+ujpNegF6ZU8KDNFiN9TbDOlRxK5R+AjwdS8ZOIa4nci77KbNF9OZuO3l/FZwiKp8IFJ1nK7uiKUjmCukL0od/6X2rJtAzJmO5Co93ZVrd5r48oqUvjklzzsBNBFmeC3oBCADEV28RKzbv3dEbOocOsJQWr1R0EHUcbS270CrQZfb9VCZWkFlQ/1ypqFFQSjmmUGbNX2CG5mivVsW6Vgm7gg8HEnVCqzL02BPY4OmylskYMFI5Bra2wRNNQBgjg39L9XU4866q3BQzJp3r0fLRVH8gHM54Jf0FVmTyHotR/Xiw5YavNy2qaQXesqqUv8HBIha0rFblbuYI/cFwOtJ47gu0QmgrU0ytDjlnmDNx4rfsNylwTIHS0Oc7Pezp7MzLmZxnTM9b5VMprAXnQr4rewXCOUKBSto+j4rD5/77DzXw96bbueNruaupb2Iy2OHXNGkB0vKFD3xHsXE2x75NBovtABEBAAHCwqwEGAEIACAWIQSNyQHOZBRsBIrVD7t5IVJSe3WSHgUCWZ4LegIbAgFACRB5IV
 JSe3WSHsB0IAQZAQgAHRYhBHsWQgTQlnI7AZY1qz6h3d2yYdl7BQJZngt6AAoJED6h3d2yYdl7CowH/Rp7GHEoPZTSUK8Ss7crwRmuAIDGBbSPkZbGmm4bOTaNs/gealc2tsVYpoMx7aYgqUW+t+84XciKHT+bjRv8uBnHescKZgDaomDuDKc2JVyx6samGFYuYPcGFReRcdmH0FOoPCn7bMW5mTPztV/wIA80LZD9kPKIXanfUyI3HLP0BPwZG4WTpKzJaalR1BNwu2oF6kEK0ymH3LfDiJ5Sr6emI2jrm4gH+/19ux/x+ST4tvm2PmH3BSQOPzgiqDiFd7RZoAIhmwr3FW4epsK9LtSxsi9gZ2vATBKO1oKtb6olW/keQT6uQCjqPSGojwzGRT2thEANH+5t6Vh0oDPZhrKUXRAAxHMBNHEaoo/M0sjZo+5OF3Ig1rMnI6XbKskLv6hu13cCymW0w/5E4XuYnyQ1cNC3pLvqDQbDx5mAPfBVHuqxJdRLQ3yDM/D2QIsxnkzQwi0FsJuni4vuJzWK/NHHDCvxMCh0YmSgbptUtgW8/niatd2Y6MbfRGxUHoctKtzqzivC8hKMTFrj4AbZhg/e9QVCsh5zSXtpWP0qFDJsxRMx0/432n9d4XUiy4U672r9Q09SsynB3QN6nTaCTWCIxGxjIb+8kJrRqTGwy/PElHX6kF0vQUWZNf2ITV1sd6LK/s/7sH+x4rzgUEHrsKr/qPvY3rUY/dQLd+owXesY83ANOu6oMWhSJnPMksbNa4tIKKbjmw3CFIOfoYHOWf3FtnydHNXoXfj4nBX8oSnkfhLILTJgf6JDFXfw6mTsv/jMzIfDs7PO1LK2oMK0+prSvSoM8bP9dmVEGIurzsTGjhTOBcb0zgyCmYVD3S48vZlTgHszAes1zwaCyt3/tOwrzU5JsRJVns+B/TUYaR/u3oIDMDygvE5ObWxXaFVnCC59r+zl0FazZ0ouyk2AYIR
 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
 YG7YEobMjX0CThKe6AV2118XNzRBw/S2IO1LWnL5qaGYPZONUa9Pj0OaErdKIk/V1wge8Zoav2fQPautBcRLW5VA33PH1ggoqKQ4ES1hc9HC6SYKzTCGixu97mu/vjOa8DYgM+33TosLyNy+bCzw62zJkMf89X0tTSdaJSj5Op0SrRvfgjbC2YpJOnXxHr9qaXFbBZQhLjemZi6zRzUNeJ6A3Nzs+gIc4H7s/bYBtcd4ugPEhDeCGffdS3TppH9PnvRXfoa5zj5bsKFgjqjWolCyAmEvd15tXz5yNXtvrpgDhjF5ozPiNp/1EeWX4DxbH2i17drVu4fXwauFZ6lcsAcJxnvCA28RlQlmEQu/gFOx1axVXf6GIuXnQSjQN6qJbByUYrdc/cFCxPO2/lGuUxnufN9Tvb51Qh54laPgGLrlD2huQeSD9Sxa0MNUjNY0qLqaReT99Ygb2LPYGSLoFVx9iZz6sZNt07LqCx9qNgsJwsdmwYsNpMuFbc7nkWjtlEqzsXZHTvYN654p43S+hcAhmmOzQZcew6h71fAJLciiqsPBnCEdgCGFAWhZZdPkMA==

After the change, the entire key fits on a single line, neat!

Autocrypt: addr=anarcat@torproject.org; prefer-encrypt=nopreference;
 keydata=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

Note that I have implemented my own kind of ridiculous Autocrypt support for the Notmuch Emacs email client I use, see this elisp code. To import keys, I pipe the message into this script which is basically just:

sq autocrypt decode   gpg --import

... thanks to Sequoia best-of-class Autocrypt support.

Note on OpenPGP usage While some have claimed OpenPGP's death, I believe those are overstated. Maybe it's just me, but I still use OpenPGP for my password management, to authenticate users and messages, and it's the interface to my YubiKey for authenticating with SSH servers. I understand people feel that OpenPGP is possibly insecure, counter-intuitive and full of problems, but I think most of those problems should instead be attributed to its current flagship implementation, GnuPG. I have tried to work with GnuPG for years, and it keeps surprising me with evilness and oddities. I have high hopes that the Sequoia project can bring some sanity into this space, and I also hope that RFC4880bis can eventually get somewhere so we have a more solid specification with more robust crypto. It's kind of a shame that this has dragged on for so long, but Update: there's a separate draft called openpgp-crypto-refresh that might actually be adopted as the "OpenPGP RFC" soon! And it doesn't keep real work from happening in Sequoia and other implementations. Thunderbird rewrote their OpenPGP implementation with RNP (which was, granted, a bumpy road because it lost compatibility with GnuPG) and Sequoia now has a certificate store with trust management (but still no secret storage), preliminary OpenPGP card support and even a basic GnuPG compatibility layer. I'm also curious to try out the OpenPGP CA capabilities. So maybe it's just because I'm becoming an old fart that doesn't want to change tools, but so far I haven't seen a good incentive in switching away from OpenPGP, and haven't found a good set of tools that completely replace it. Maybe OpenSSH's keys and CA can eventually replace it, but I suspect they will end up rebuilding most of OpenPGP anyway, just more slowly. If they do, let's hope they avoid the mistakes our community has done in the past at least...

$ grep kermit /etc/services
kermit          1649/tcp

Serial Ports and Modems In my piece The PC & Internet Revolution in Rural America, I recently talked about getting a modem what an excitement it was to get one! I realize that many people today have never used a serial line or a modem, so let s briefly discuss. Before Ethernet and Wifi took off in a big way, in the 1990s-2000s, two computers would talk to each other over a serial line and a modem. By modern standards, these were slow; 300bps was a common early speed. They also (at least in the beginning) had no kind of error checking. Characters could be dropped or changed. Sometimes even those speeds were faster than the receiving device could handle. Some serial links were 7-bit, and wouldn t even pass all 7-bit characters; for instance, sending a Ctrl-S could lock up a remote until you sent Ctrl-Q. And computers back in the 1970s and 1980s weren t as uniform as they are now. They used different character sets, different line endings, and even had different notions of what a file is. Today s notion of a file as whatever set of binary bytes an application wants it to be was by no means universal; some systems treated a file as a set of fixed-length records, for instance. So there were a lot of challenges in reliably moving files between systems. Kermit was introduced to reliably move files between systems using serial lines, automatically working around the varieties of serial lines, detecting errors and retransmitting, managing transmit speeds, and adapting between architectures as appropriate. Quite a task! And perhaps this explains why it was supported on a calculator with a primitive CPU by today s standards. Serial communication, by the way, is still commonplace, though now it isn t prominent in everyone s home PC setup. It s used a lot in industrial equipment, avionics, embedded systems, and so forth. The key point about serial lines is that they aren t inherently multiplexed or packetized. Whereas an Ethernet network is designed to let many dozens of applications use it at once, a serial line typically runs only one (unless it is something like PPP, which is designed to do multiplexing over the serial line). So it become useful to be able to both log in to a machine and transfer files with it. That is, incidentally, still useful today.

Kermit and XModem/ZModem I wondered: why did we end up with two diverging sets of protocols, created at about the same time? The Kermit website has the answer: essentially, BBSs could assume 8-bit clean connections, so XModem and ZModem had much less complexity to worry about. Kermit, on the other hand, was highly flexible. Although ZModem came out a few years before Kermit had its performance optimizations, by about 1993 Kermit was on par or faster than ZModem.

Beyond serial ports As LANs and the Internet came to be popular, people started to use telnet (and later ssh) to connect to remote systems, rather than serial lines and modems. FTP was an early way to transfer files across the Internet, but it had its challenges. Kermit added telnet support, as well as later support for ssh (as a wrapper around the ssh command you already know). Now you could easily log in to a machine and exchange files with it without missing a beat. And so it was that the Internet Kermit Service Daemon (IKSD) came into existence. It allows a person to set up a Kermit server, which can authenticate against local accounts or present anonymous access akin to FTP. And so I established the quux.org Kermit Server, which runs the Unix IKSD (part of the Debian ckermit package).

Trying Out the quux.org Kermit Server There are more instructions on the quux.org Kermit Server page! You can connect to it using either telnet or the kermit program. I won t duplicate all of the information here, but here s what it looks like to connect:

$ kermit
C-Kermit 10.0 Beta.08, 15 Dec 2022, for Linux+SSL (64-bit)
 Copyright (C) 1985, 2022,
  Trustees of Columbia University in the City of New York.
  Open Source 3-clause BSD license since 2011.
Type ? or HELP for help.
(/tmp/t/) C-Kermit>iksd /user:anonymous kermit.quux.org
 DNS Lookup...  Trying 135.148.101.37...  Reverse DNS Lookup... (OK)
Connecting to host glockenspiel.complete.org:1649
 Escape character: Ctrl-\ (ASCII 28, FS): enabled
Type the escape character followed by C to get back,
or followed by ? to see other options.
----------------------------------------------------

 >>> Welcome to the Internet Kermit Service at kermit.quux.org <<<

To log in, use 'anonymous' as the username, and any non-empty password

Internet Kermit Service ready at Fri Aug  4 22:32:17 2023
C-Kermit 10.0 Beta.08, 15 Dec 2022
kermit

Enter e-mail address as Password: [redacted]

Anonymous login.

You are now connected to the quux kermit server.

Try commands like HELP, cd gopher, dir, and the like.  Use INTRO
for a nice introduction.

(~/) IKSD>

You can even recursively download the entire Kermit mirror: over 1GB of files!

Conclusions So, have fun. Enjoy this experience from the 1980s. And note that Kermit also makes a better ssh client than ssh in a lot of ways; see ideas on my Kermit page. This page also has a permanent home on my website, where it may be periodically updated.

Kaalkoot This post would be mature and would talk about death and other things. So if there are young kids or whatever kindly refrain from reading it. Just saw this series in 2 days. In a way the series encompasses all that which is wrong in India and partly the World perhaps. IMDB describes it as A police officer must deal with society s and his mother s pressure to marry, as well as frequent bullying and pressure from his superiors. But that hardly does justice to either the story or the script or the various ebbs and flows it takes. A very bit part of the series of the series is about patriarchy and the various forms it takes. It tells how we would use women and then throw them, many a times by willing relatives who want to save face . And it s so many ways and so many times that people do not even pay attention. I will not share the story as it needs to be experienced as well as the many paths the story takes as well as many paths it could have taken. What is remarkable about this series is that everyone is grey apart from the women who are victims in all of these. Even our hero, the protagonist uses it to take advantage of a woman. There are multiple stories and timelines that are just touched upon. For e.g. curing the gay and boasting he has cured many guys and now have their married with families. How many families suffered god only knows, both sexes dissatisfied At the end of the series while a slightly progressive end is shown, in reality you are left wondering whether the decision taken by the protagonist and the woman having just no agency. The hero knowing he is superior to her because of her perceived weakness. A deep-rooted malaise that is difficult to break out of. His father too and the relationship the hero longs for to have with his father who is no more. He does share some of his feelings with his mum, which touches the cord of probably every child whose mother father left them early and all those things they wanted to talk or would have chatted out if they knew this would be the last conversation they will ever have with them. Couldn t even say sorry for all the wrongs and the pain we have given them. There are just too many layers in the webseries that I would need to see it a few times to be aware of. I could sense the undercurrents but sometimes you need to see such series or movies multiple times to understand them or it could simply be the case of me being just too thick. There are also poems and poems as we know may have multiple meanings and is or can be more contextual to the person reading it rather than the creator. At the end, while it does show a positive end, in reality I feel there is no redemption for us. I am talking about men. We are too proud, too haughty and too insecure. And if things don t go the way we want, it s the women who pay the price I am not going to talk about any news either about Manipur or anywhere else because hate crimes have become normal. An RPF personnel plans, and goes from coach to coach to find Muslims and shoot them and then say only the tallest leaders in RW should be voted for. A mob then burns down Muslim s homes and businesses, all par for the course. The mentally unstable moniker taken right from the American far-right notebook.

The Americans have taken it much further than anyone else using open carry and stand your ground, laws to make blacks afraid and going further. I don t really wanna go down that route as it s a whole another pandora s box and what little I have read tells me it starts from the very beginning when the European settlers invaded America and took indigenous people s lands and giving it the moniker of Wild West . Just too much to deal with.

Mental Health But these spate of bad news, of murders, rapes and whatnot does take a toll on the mental health of people. Take this tweet as instance

I think the above tweet is an expression that is felt by many Indians, whatsoever their religion might be. Most of them unable to express it as many have responsibilities in which they are the only caretakers or the only earner in the family. So even though, we have huge inflation especially in foods and whatnot the daily struggle to put food on the table extinguishes everything else. And for those who may want to go through for whatever reasons, there is nothing like MAID in India. There was a good debate that I saw few months ago about it, and I think both the for and against miss a very crucial point. People have their own idea or imagination of what dignity in living as well as dignity of dying. I was seeing some videos of NHS doctors (UK) where many doctors couldn t do anything as their patients died as they couldn t pay bills for heating. Many of the patients wanted the doctors to end their suffering. The case against it is that people should reach out and have community services. While that is a great theory, practically it is difficult. Whether it is in dense populated area like Pune (population around 10 odd million) or the whole country of Japan which is heavily being depopulated, in both the extreme scenarios the access to mental health is and would be low. And even if there is someway that the Government, the community, business community etc. come altogether and solve it, it just shifts the problem. All the shit, our fears, our uncertainties, our doubts we unload on the medical health professional but where do they go to get rid of it. It s a vicious circular problem. I did read somewhere that mental health professionals are four times prone to suicide than other doctors. And all emergency care professionals like firefighters and whatnot are again 4 times more likely to commit suicide than the general population. How much those stats are true, have no clue as again most of such kinds of data is not collected by NCRB (National Crime Records Bureau) in India. In fact, NCRB often describes such deaths as accidental deaths as otherwise the person would be termed as loser or something else. Even in and after death, people are worried about labels. But that I guess is what s it all about. I do not know but do guess most of the 160 odd countries would have similar issues and most of them keep quiet about it. Till later

Manipur Videos Warning: The text might be mature and will have references to violence so if there are kids or you are sensitive, please excuse. Few days back, saw the videos and I cannot share the rage, shame and many conflicting emotions that were going through me. I almost didn t want to share but couldn t stop myself. The woman in the video were being palmed, fingered, nude, later reportedly raped and murdered. And there have been more than a few cases. The next day saw another video that showed beheaded heads, and Kukis being killed just next to their houses. I couldn t imagine what those people must be feeling as the CM has been making partisan statements against them. One of the husbands of the Kuki women who had been paraded, fondled is an Army Officer in the Indian Army. The Meiteis even tried to burn his home but the Army intervened and didn t let it get burnt. The CM s own statement as shared before tells his inability to bring the situation out of crisis. In fact, his statement was dumb stating that the Internet shutdown was because there were more than 100 such cases. And it s spreading to the nearby Northeast regions. Now Mizoram, the nearest neighbor is going through similar things where the Meitis are not dominant. The Mizos have told the Meitis to get out. To date, the PM has chosen not to visit Manipur. He just made a small 1 minute statement about it saying how the women have shamed India, an approximation of what he said.While it s actually not the women but the men who have shamed India. The Wire has been talking to both the Meitis, the Kukis, the Nagas. A Kuki women sort of bared all. She is right on many counts. The GOI while wanting to paint the Kukis in a negative light have forgotten what has been happening in its own state, especially its own youth as well as in other states while also ignoring the larger geopolitics and business around it. Taliban has been cracking as even they couldn t see young boys, women becoming drug users. I had read somewhere that 1 in 4 or 1 in 5 young person in Afghanistan is now in its grip. So no wonder,the Taliban is trying to eradicate and shutdown drug use among it s own youth. Circling back to Manipur, I was under the wrong impression that the Internet shutdown is now over. After those videos became viral as well as the others I mentioned, again the orders have been given and there is shutdown. It is not fully shut but now only Govt. offices have it. so nobody can share a video that goes against any State or Central Govt. narrative A real sad state of affairs Update: There is conditional reopening whatever that means When I saw the videos, the first thing is I felt was being powerless, powerless to do anything about it. The second was if I do not write about it, amplify it and don t let others know about it then what s the use of being able to blog

Mental Health, Binging on various Webseries Both the videos shocked me and I couldn t sleep that night or the night after. it. Even after doing work and all, they would come in unobtrusively in my nightmares While I felt a bit foolish, I felt it would be nice to binge on some webseries. Little I was to know that both Northshore and Alaska Daily would have stories similar to what is happening here While the story in Alaska Daily is fictional it resembles very closely to a real newspaper called Anchorage Daily news. Even there the Intuit women , one of the marginalized communities in Alaska. The only difference I can see between GOI and the Alaskan Government is that the Alaskan Government was much subtle in doing the same things. There are some differences though. First, the State is and was responsive to the local press and apart from one close call to one of its reporters, most reporters do not have to think about their own life in peril. Here, the press cannot look after either their livelihood or their life. It was a juvenile kid who actually shot the video, uploaded and made it viral. One needs to just remember the case details of Siddique Kappan. Just for sharing the news and the video he was arrested. Bail was denied to him time and time again citing that the Police were investigating . Only after 2 years and 3 months he got bail and that too because none of the charges that the Police had they were able to show any prima facie evidence. One of the better interviews though was of Vrinda Grover. For those who don t know her, her Wikipedia page does tell a bit about her although it is woefully incomplete. For example, most recently she had relentlessly pursued the unconstitutional Internet Shutdown that happened in Kashmir for 5 months. Just like in Manipur, the shutdown was there to bury crimes either committed or being facilitated by the State. For the issues of livelihood, one can take the cases of Bipin Yadav and Rashid Hussain. Both were fired by their employer Dainik Bhaskar because they questioned the BJP MP Smriti Irani what she has done for the state. The problems for Dainik Bhaskar or for any other mainstream media is most of them rely on Government advertisements. Private investment in India has fallen to record lows mostly due to the policies made by the Centre. If any entity or sector grows a bit then either Adani or Ambani will one way or the other take it. So, for most first and second generation entrepreneurs it doesn t make sense to grow and then finally sell it to one of these corporates at a loss GOI on Adani, Ambani side of any deal. The MSME sector that is and used to be the second highest employer hasn t been able to recover from the shocks of demonetization, GST and then the pandemic. Each resulting in more and more closures and shutdowns. Most of the joblessness has gone up tremendously in North India which the Government tries to deny. The most interesting points in all those above examples is within a month or less, whatever the media reports gets scrubbed. Even the firing of the journos that was covered by some of the mainstream media isn t there anymore. I have to use secondary sources instead of primary sources. One can think of the chilling effects on reportage due to the above. The sad fact is even with all the money in the world the PM is unable to come to the Parliament to face questions.

The above poster/question is by Surya Pratap Singh, a retired IAS officer. He asks why the PM is unable to answer in either of the houses. As shared before, the Govt. wants very limited discussion. Even yesterday, the Lok Sabha TV just showed the BJP MP s making statements but silent or mic was off during whatever questions or statements made by the opposition. If this isn t mockery of Indian democracy then I don t know what is Even the media landscape has been altered substantially within the last few years. Both Adani and Ambani have distributed the media pie between themselves. One of the last bastions of the free press, NDTV was bought by Adani in a hostile takeover. Both Ambani and Adani are close to this Goverment. In fact, there is no sector in which one or the other is not present. Media houses like Newsclick, The Wire etc. that are a fraction of mainstream press are where most of the youth have been going to get their news as they are not partisan. Although even there, GOI has time and again interfered. The Wire has had too many 504 Gateway timeouts in the recent months and they had been forced to move most of their journalism from online to video, rather Youtube in order to escape both the censoring and the timeouts as shared above. In such a hostile environment, how both the organizations are somehow able to survive is a miracle. Most local reportage is also going to YouTube as that s the best way for them to not get into Govt. censors. Not an ideal situation, but that s the way it is. The difference between Indian and Israeli media can be seen through this

The above is a Screenshot shared by how the Israeli media has reacted to the Israeli Government s Knesset over the judicial overhaul . Here, the press itself erodes its own by giving into the Government day and night

Binging on Webseries Saw Northshore, Three Pines, Alaska Daily and Doogie Kamealoha M.D. which is based on Doogie Howser M.D. Of the four, enjoyed Doogie Kamealoha M.D. the most but then it might be because it s a copy of Doogie Howser, just updated to the new millenia and there are some good childhood memories associated with that series. The others are also good. I tried to not see European stuff as most of them are twisted and didn t want that space.

EU Digital Operational Resilience Act and impact on FOSS Few days ago, apparently the EU shared the above Act. One can read about it more here. This would have more impact on FOSS as most development of various FOSS distributions happens in EU. Fair bit of Debian s own development happens in Germany and France. While there have been calls to make things more clearer, especially for FOSS given that most developers do foss development either on side or as a hobby while their day job is and would be different. The part about consumer electronics and FOSS is a tricky one as updates can screw up your systems. Microsoft has had a huge history of devices not working after an update or upgrade. And this is not limited to Windows as they would like to believe. Even apple seems to be having its share of issues time and time again. One would have hoped that these companies that make billions of dollars from their hardware and software sales would be doing more testing and Q&A and be more aware about security issues. FOSS, on the other hand while being more responsive doesn t make as much money vis-a-vis the competitors. Let s take the most concrete example. The most successful mobile phone having FOSS is Purism. But it s phone, it has priced itself out of the market. A huge part of that is to do with both economies of scale and trying to get an infrastructure and skills in the States where none or minimally exists. Compared that to say Pinepro that is manufactured in Hong Kong and is priced 1/3rd of the same. For most people it is simply not affordable in these times. Add to that the complexity of these modern cellphones make it harder, not easier for most people to be vigilant and update the phone at all times. Maybe we need more dumphones such as Light and Punkt but then can those be remotely hacked or not, there doesn t seem to be any answers on that one. I haven t even seen anybody even ask those questions. They may have their own chicken and egg issues. For people like me who have lost hearing, while I can navigate smartphones for now but as I become old I don t see anything that would help me. For many an elderly population, both hearing and seeing are the first to fade. There doesn t seem to be any solutions targeted for them even though they are 5-10% of any population at the very least. Probably more so in Europe and the U.S. as well as Japan and China. All of them are clearly under-served markets but dunno a solution for them. At least to me that s an open question.

RISC -V Motherboard, SBC While I didn t want to, a part of me is hyped about this motherboard. This would probably be launched somewhere in November. There are obvious issues in this, the first being unlike regular motherboards you wouldn t be upgrade as you would do.You can t upgrade your memory, can t upgrade the CPU (although new versions of instructions could be uploaded, similar to BIOS updates) but as the hardware is integrated (the quad-core SiFive Performance P550 core complex) it would really depend. If the final pricing is around INR 4-5k then it may be able to sell handsomely provided there are people to push and provide support around it. A 500 GB or 1 TB SSD coupled with it and a cheap display unit and you could use it anywhere although as the name says it s more for tinkering as the name suggests. Another board that could perhaps be of more immediate use would be the beagleboard. They launched the same couple of days back and called it Beagle V-Ahead. Again, costs are going to be a concern. Just a year before the pandemic the Beagleboard Black (BB) used to cost in the sub 4k range, today it costs 8k+ for the end user, more than twice the price. How much Brexit is to be blamed for this and how much the Indian customs we would never know. The RS Group that is behind that shop is head-quartered in the UK. As said before, we do not know the price of either board as it probably will take few months for v-ahead to worm its way in the Indian market, maybe another 6 months or so. Even so, with the limited info. on both the boards, I am tilting more towards the other HiFive one. We should come to know about the boards say in 3-5 months of time.

CHIPS Act I had shared about the Chips Act a few times here as well as on SM. Two articles do tell how the CHIPS Act 2023 is more of a political tool, an industrial defence policy rather than just business as most people tend to think.

Cancelation of Books, Books Burning etc. Almost 2400 years ago, Plato released his work called Plato s Republic and one of the seminal works within it is perhaps one of the most famous works was the Allegory of the Cave. That is used again and again in a myriad ways, mostly in science-fiction though and mostly to do with utopian, dystopian movies, webseries etc. I did share how books are being canceled in the States, also a bit here. But the most damning thing has happened throughout history, huge quantities of books burned almost all for politics But part of it has been neglect as well as this time article shares. What we have lost and continue to lose is just priceless. Every book has a grain of truth in it, some more, some less but equally enjoyable. Most harmful is the neglect towards books and is more true today than any other time in history. Kids today have a wide variety of tools to keep themselves happy or occupied, from anime, VR, gaming the list goes on and on. In that scenario, how the humble books can compete. People think of Kindle but most e-readers like Kindle are nothing but obsolescence by design. I have tried out Kindle a few times but find it a bit on the flimsy side. Books are much better IMHO or call me old-school. While there are many advantages, one of the things that I like about books is that you can easily put yourself in either the protagonist or the antagonist or somewhere in the middle and think of the possible scenarios wherever you are in a particular book. I could go on but it will be a blog post or two in itself. Till later. Happy Reading.

Update:Manipur Extremely horrifying visuals, articles and statements continue to emanate from Manipur. Today, 19th July 2023, just couple of hours back, a video surfaced showing two Kuki women were shown as stripped, naked and Meitei men touching their private parts. Later on, we came to know that this was in response of a disinformation news spread by the Meitis of few women being raped although no documentary evidence of the same surfaced, no names nothing. While I don t want to share the video I will however share the statement shared by the Kuki-Zo tribal community on that. The print gives a bit more context to what has been going on.

Update, Few hours later : The Print also shared more of a context about six days ago. The reason we saw the video now was that for the last 2.5 months Manipur was in Internet shutdown so those videos got uploaded now. There was huge backlash from the Twitter community and GOI ordered the Manipur Police to issue this Press Release yesterday night or just few hours before with yesterday s time-stamp.

IndianExpress shared an article that does state that while an FIR had been registered immediately no arrests so far and this is when you can see the faces of all the accused. Not one of them tried to hide their face behind a mask or something. So, if the police wanted, they could have easily identified who they are. They know which community the accused belong to, they even know from where they came. If they wanted to, they could have easily used mobile data and triangulation to find the accused and their helpers. So, it does seem to be attempt to whitewash and protect a certain community while letting it prey on the other. Another news that did come in, is because of the furious reaction on Twitter, Youtube has constantly been taking down the video as some people are getting a sort of high more so from the majoritarian community and making lewd remarks. Twitter has been somewhat quick when people are making lewd remarks against the two girl/women. Quite a bit of the above seems like a cover-up. Lastly, apparently GOI has agreed to having a conversation about it in Lok Sabha but without any voting or passing any resolutions as of right now. Would update as an when things change. Update: Smriti Irani, the Child and Development Minister gave the weakest statement possible

As can be noticed, she said sexual assault rather than rape. The women were under police custody for safety when they were whisked away by the mob. No mention of that. She spoke to the Chief Minister who has been publicly known as one of the provocateurs or instigators for the whole thing. The CM had publicly called the Kukus and Nagas as foreigners although both of them claim to be residing for thousands of years and they apparently have documentary evidence of the same . Also not clear who is doing the condemning here. No word of support for the women, no offer of intervention, why is she the Minister of Child and Women Development (CDW) if she can t use harsh words or give support to the women who have gone and going through horrific things Update : CM Biren Singh s Statement after the video surfaced

This tweet is contradictory to the statements made by Mr. Singh couple of months ago. At that point in time, Mr. Singh had said that NIA, State Intelligence Departments etc. were giving him minute to minute report on the ground station. The Police itself has suo-moto (on its own) powers to investigate and apprehend criminals for any crime. In fact, the Police can call for questioning of anybody in any relation to any crime and question them for upto 48 hours before charging them. In fact, many cases have been lodged where innocent persons have been framed or they have served much more in the jail than the crime they are alleged to have been committed. For e.g. just a few days before there was a media report of a boy who has been in jail for 3 years. His alleged crime, stealing mere INR 200/- to feed himself. Court doesn t have time to listen to him yet. And there are millions like him. The quint eloquently shares the tale where it tells how both the State and the Centre have been explicitly complicit in the incidents ravaging Manipur. In fact, what has been shared in the article has been very true as far as greed for land is concerned. Just couple of weeks back there have been a ton of floods emanating from Uttarakhand and others. Just before the flooding began, what was the CM doing can be seen here. Apart from the newspapers I have shared and the online resources, most of the mainstream media has been silent on the above. In fact, they have been silent on the Manipur issue until the said video didn t come into limelight. Just now, in Lok Sabha everybody is present except the Prime Minister and the Home Minister. The PM did say that the law will take its own course, but that s about it. Again no support for the women concerned. Update: CJI (Chief Justice of India) has taken suo-moto cognizance and has warned both the State and Centre to move quickly otherwise they will take the matter in their own hand.

Update: Within 2 hours of the CJI taking suo-moto cognizance, they have arrested one of the main accused Heera Das

The above tells you why the ban on Internet was put in the first place. They wanted to cover it all up. Of all the celebs, only one could find a bit of spine, a bit of backbone to speak about it, all the rest mum

Just imagine, one of the women is around my age while the young one could have been a daughter if I had married on time or a younger sister for sure. If ever I came face to face with them, I just wouldn t be able to look them in the eye. Even their whole whataboutery is built on sham. From their view Kukis are from Burma or Burmese descent. All of which could be easily proved by DNA of all. But let s leave that for a sec. Let s take their own argument that they are Burmese. Their idea of Akhand Bharat stretches all the way to Burma (now called Myanmar). They want all the land but no idea with what to do with the citizens living on it. Even after the video, the whataboutery isn t stopping, that shows how much hatred is there. And not knowing that they too will be victim of the same venom one or the other day Update: Opposition was told there would be a debate on Manipur. The whole day went by, no debate. That s the shamelessness of this Govt. Update 20th July 19:25 Center may act or not act against the perpetrators but they will act against Twitter who showed the crime. Talk about shooting the messenger

We are now in the last stage. In 2014, we were at 6

1. Get the official installation image from the usual locations. I got the netinst CD image via BitTorrent.
2. Boot from the image and go through the installation in the normal way.
   1. You may want to select an alternative desktop environment (and unselect GNOME). These steps have been tested with MATE.
   2. Stop when you are asked to remove the installation media and reboot.
3. Press Alt + Right arrow to switch to the text VC. Hit return to activate the console and run the following commands (answering yes as appropriate):

chroot /target bash
apt-get install sysvinit-core elogind ntp dbus-x11
apt-get autoremove
exit

4. Observe the output from the apt-get install. If your disk arrangements are unusual, that may generate some error messages from update-initramfs.
5. Go back to the installer VC with Alt + Left arrow. If there were no error messages above, you may tell it to reboot.
6. If there were error messages (for example, I found that if there was disk encryption, alarming messages were printed), tell the installer to go Back . Then ask it to Install GRUB bootloader (again). After that has completed, you may reboot.
7. Enjoy your Debian system without systemd.

Welcome to the June 2023 report from the Reproducible Builds project In our reports, we outline the most important things that we have been up to over the past month. As always, if you are interested in contributing to the project, please visit our Contribute page on our website.

Corrupted build environments can deliver compromised cryptographically signed binaries. Several exploits in critical supply chains have been demonstrated in recent years, proving that this is not just theoretical. The most well secured build environments are still single points of failure when they fail. [ ] This talk will focus on the state of the art from several angles in related Free and Open Source Software projects, what works, current challenges and future plans for building trustworthy toolchains you do not need to trust.

The 2020 Solarwinds attack was a tipping point that caused a heightened awareness about the security of the software supply chain and in particular the large amount of trust placed in build systems. Reproducible Builds (R-Bs) provide a strong foundation to build defenses for arbitrary attacks against build systems by ensuring that given the same source code, build environment, and build instructions, bitwise-identical artifacts are created.

We conducted a series of 24 semi-structured expert interviews with participants from the Reproducible-Builds.org project, and iterated on our questions with the reproducible builds community. We identified a range of motivations that can encourage open source developers to strive for R-Bs, including indicators of quality, security benefits, and more efficient caching of artifacts. We identify experiences that help and hinder adoption, which heavily include communication with upstream projects. We conclude with recommendations on how to better integrate R-Bs with the efforts of the open source and free software community.

• Martin Monperrus asked whether there are any project[s] where reproducibility is checked in a continuous integration pipeline? which received a number of replies from various projects.
• Vagrant Cascadian mentioned that Packaging Con 2023 is being held in Berlin, the weekend before the Reproducible Builds summit later this year. In particular, Vagrant noticed that the Call for Proposals (CFP) closes at the end of July.
• Larry Doolittle was searching Usenet archives and discovered a thread from December 1999 titled Time independent checksum(cksum) on comp.unix.programming. Larry notes that it starts with Jayan asking about comparing binaries that might have difference in their embedded timestamps (that is, perhaps, Foreshadowing diffoscope, amiright? ) and goes on to observe that:

The antagonist is David Schwartz, who correctly says There are dozens of complex reasons why what seems to be the same sequence of operations might produce different end results, but goes on to say I totally disagree with your general viewpoint that compilers must provide for reproducability [sic]. Dwight Tovey and I (Larry Doolittle) argue for reproducible builds. I assert Any program especially a mission-critical program like a compiler that cannot reproduce a result at will is broken. Also it s commonplace to take a binary from the net, and check to see if it was trojaned by attempting to recreate it from source.

Distribution work 27 reviews of Debian packages were added, 40 were updated and 8 were removed this month adding to our knowledge about identified issues. A new randomness_in_documentation_generated_by_mkdocs toolchain issue was added by Chris Lamb [ ], and the deterministic flag on the paths_vary_due_to_usrmerge issue as we are not currently testing usrmerge issues [ ] issues.
Roland Clobus posted his 18th update of the status of reproducible Debian ISO images on our mailing list. Roland reported that all major desktops build reproducibly with bullseye, bookworm, trixie and sid , but he also mentioned amongst many changes that not only are the non-free images being built (and are reproducible) but that the live images are generated officially by Debian itself. [ ]
Jan-Benedict Glaw noticed a problem when building NetBSD for the VAX architecture. Noting that Reproducible builds [are] probably not as reproducible as we thought , Jan-Benedict goes on to describe that when two builds from different source directories won t produce the same result and adds various notes about sub-optimal handling of the CFLAGS environment variable. [ ]
F-Droid added 21 new reproducible apps in June, resulting in a new record of 145 reproducible apps in total. [ ]. (This page now sports missing data for March May 2023.) F-Droid contributors also reported an issue with broken resources in APKs making some builds unreproducible. [ ]
Bernhard M. Wiedemann published another monthly report about reproducibility within openSUSE

---

Upstream patches

• Bernhard M. Wiedemann:
  • bcachefs (sort find / filesys)
  • build-compare (reports files as identical)
  • build-time (toolchain date)
  • cockpit (merged, gzip mtime)
  • gcc13 (gcc13 toolchain LTO parallelism)
  • ghc-rpm-macros (toolchain parallelism)
  • golangcli-lint (date)
  • gutenprint (date+time)
  • mage (date (golang))
  • mumble (filesys)
  • pcr (date)
  • python-nss (drop sphinx .doctrees)
  • python310 (merged, bisected+backported)
  • warpinator (merged, date)
  • xroachng (date)
• Chris Lamb:
  • #1037159 filed against elinks.
  • #1037205 filed against multipath-tools.
  • #1037216 filed against mkdocstrings-python-handlers.
  • #1038730 filed against fribidi.
  • #1038957 filed against jtreg7.
  • #1039932 filed against python-bitstring (forwarded upstream).
• Vagrant Cascadian:
  • #1037235 filed against gradle-kotlin-dsl.
  • #1037240 filed against libsdl-console.
  • #1037267 filed against kawari8.
  • #1037269 filed against freetds.
  • #1037272 filed against gbrowse.
  • #1037276 filed against bglibs.
  • #1037277 filed against advi.
  • #1037278 filed against afterstep.
  • #1037280 filed against simstring.
  • #1037296 filed against manderlbot.
  • #1037298 filed against erlang-proper.
  • #1037300 filed against comedilib.
  • #1037309 filed against libint.
  • #1037427 filed against newlib.
  • #1038908 filed against binutils-msp430.
  • #1038970 & #1038971 filed against c-munipack.
  • #1039044 filed against python-marshmallow-sqlalchemy.
  • #1039457 filed against mplayer.
  • #1039493 & #1039500 filed against menu.
  • #1039506 filed against mini-buildd.
  • #1039610 filed against pnetcdf.
  • #1039617 & #1039618 filed against liblopsub.
  • #1039619 filed against wcc.
  • #1039623 filed against shotcut.
  • #1039624 filed against icu.
  • #1039741 filed against libapache-poi-java.
  • #1039808 filed against atf.
  • #1039865 filed against valgrind.

---

Testing framework The Reproducible Builds project operates a comprehensive testing framework (available at tests.reproducible-builds.org) in order to check packages and other artifacts for reproducibility. In June, a number of changes were made by Holger Levsen, including:

• Additions to a (relatively) new Documented Jenkins Maintenance (djm) script to automatically shrink a cache & save a backup of old data [ ], automatically split out previous months data from logfiles into specially-named files [ ], prevent concurrent remote logfile fetches by using a lock file [ ] and to add/remove various debugging statements [ ].
• Updates to the automated system health checks to, for example, to correctly detect new kernel warnings due to a wording change [ ] and to explicitly observe which old/unused kernels should be removed [ ]. This was related to an improvement so that various kernel issues on Ubuntu-based nodes are automatically fixed. [ ]

Holger and Vagrant Cascadian updated all thirty-five hosts running Debian on the amd64, armhf, and i386 architectures to Debian bookworm, with the exception of the Jenkins host itself which will be upgraded after the release of Debian 12.1. In addition, Mattia Rizzolo updated the email configuration for the @reproducible-builds.org domain to correctly accept incoming mails from jenkins.debian.net [ ] as well as to set up DomainKeys Identified Mail (DKIM) signing [ ]. And working together with Holger, Mattia also updated the Jenkins configuration to start testing Debian trixie which resulted in stopped testing Debian buster. And, finally, Jan-Benedict Glaw contributed patches for improved NetBSD testing.

---

If you are interested in contributing to the Reproducible Builds project, please visit our Contribute page on our website. However, you can get in touch with us via:

• IRC: #reproducible-builds on irc.oftc.net.
• Mailing list: rb-general@lists.reproducible-builds.org
• Twitter: @ReproBuilds

Motherboard Battery You know you have become too old when you get stumped and the solution is simple and fixed by the vendor. About a week back, I was getting CPU Fan Error. It s a 6 year old desktop so I figured that the fan or the ball bearings on the fan must have worn out. I opened up the cabinet and I could see both the on cpu fan was working coolly as well as the side fan was working without an issue. So I couldn t figure out what was the issue. I had updated the BIOS/UEFI number of years ago so that couldn t be an issue. I fiddled with the boot menu and was able to boot into Linux but it was a pain that I had to do every damn time. As it is, it takes almost 2-3 minutes for the whole desktop to be ready and this extra step was annoying. I had bought a Mid-tower cabinet while the motherboard so there were alternate connectors I could try but still the issue persisted. And this workaround was heart-breaking as you boot the BIOS/UEFI and fix the boot menu each time even though it had Debian Boot Launcher and couple of virtual ones provided by the vendor (Asus) and they were hardwired. So failing all, went to my vendor/support and asked if he could find out what the issue is. It costed me $10, he did all the same things I did but one thing more, he changed the battery (cost less than 1USD) and presto all was right with the world again. I felt like a fool but a deal is a deal so paid the gentleman for his services. Now can again use the desktop and at least know about what s happening in the outside world.

Framework Laptops I have been seeing quite a few teardowns of Framework Laptops on Youtube and love it. More so, now that they have AMD in their arsenal. I do hope they work on their pricing and logistics and soon we have it here competing with others. If the pricing isn t substantial then definitely would be one of the first ones to order. India is and remains a very cost-conscious market and more so with the runaway prices that we have been seeing. In fact, the last 3 years have been pretty bad for the overall PC market declining 30% YoY for the last 3 years while prices have gone through the roof. Apart from the pricing from the vendors, taxation has been another hit as the current Govt. has been taxing anywhere from 30-100% taxes on various PC, desktop and laptop components. Think have shared Graphic cards for instance have 100% Duty apart from other taxes. I don t see the market picking up at least in the 24 to 36 months. Most of this year and next year, both AMD and Intel are doing refreshes so while there would be some improvements (probably 10-15%) not earth-shattering for the wider market to sit up and take notice. Intel has proposed a 64-bit architecture (only) about couple of months back, more on that later. As far as the Indian market is concerned, if you want the masses, then have lappies at around 40-50k ($600 USD) and there would be a mass takeup, if you want to be a Lenovo or something like that, then around a lakh or INR 100k ($1200 USD) or be an Apple which is around 150k INR or around 2000 USD. There are some clues as to what their plans but for that you have to trawl their forums and the knowledgebase. Seems some people are using freight forwarders to get around the hurdles but Framework doesn t want to do any shortcuts for the same. Everybody seems to be working on Vertical stacking of chips, whether it is the Chinese, or Belgian s or even AMD and Intel who have their own spins to it, but most of these technologies are at least 3-4 years out in the future (or more). India is a big laggard in this space with having knowledge of 45nm which in Aviation speak one could say India knows how to build 707 (one of the first Boeing commercial passenger carrying aircraft) while today it is Boeing 777x or Airbus 350. I have shared in the past how the Tata s have been trying to collaborate with the Japanese and get at least their 25nm chip technology but nothing has come of it to date. The only somewhat o.k. news has been the chip testing and packaging plant by Micron to be made in Gujarat. It doesn t do anything for us although we would be footing almost 70% of the plant s capital expenditure and the maximum India will get 4k jobs. Most of these plants are highly automated as dust is their mortal enemy so even the 4k jobs announced seem far-fetched. It would probably be less than half once production starts if it happens but that is probably a story for another time. Just as a parting shot, even memory vendors are going highly automated factory lines.

VR Headsets I was stuck by how similar or where VR is when I was watching Made in Finland. I don t want to delve much into the series but it is a fascinating one. I was very much taken by the character of Kari Kairamo or the actor who played the character of him and was very much disappointed with the sad ending the gentleman got. It is implicated in the series that the banks implicitly forced him to commit suicide. There is also a lot of chaos as is normal in a big company having many divisions. It s only when Jorma Olila takes over, the company sheds a lot of dead weight was cut off with mobiles having the most funding which they didn t have before. I was also fascinated when I experienced pride when Nokia shows off its 1011 mobile phone when at that time phones were actually like bricks. My first Nokia was number of years later, Nokia 1800 and have to say those phones outlasted a long time than today s Samsung s. If only Nokia had read the tea leaves right Back to the topic though, I have been wearing glasses since the age of 5 year old. They weigh less than 10 grams and you still get a nose dent. And I know enough people, times etc. when people have got headaches and whatnot from glasses. Unless the VR headsets become that size and don t cost an arm and leg (or a kidney or a liver) it would have niche use. While 5G and 6G would certainly push more ppl to get it it probably would take a few more years before we have something that is simple and doesn t need too much to get it rolling. The series I mentioned above is already over it s first season but would highly recommend it. I do hope the second season happens quickly and we do come to know why and how Nokia missed the Android train and their curious turn to get to Microsoft which sorta sealed their fate

Steam I have been following Steam, Luthris and plenty of other launchers on Debian. There also seems to some sort of an idea that once MESA 23.1.x or later comes into Debian at some point we may get Steam 64-bit and some people are hopeful that we may get it by year-end. There are a plethora of statistics that can be used to find status of Gaming on Linux. This is perhaps the best one I got so far. Valve also has its own share of stats that it shows here. I am not going to go into much detail except the fact that lutris has been there on Debian sometime now. And as and when Steam does go fully 64-bit, whole lot of multilib issues could be finally put to rest. Interestingly, Intel has quietly also shared details of only a 64-bit architecture PC. From what I could tell, it simply boots into 16-bit and then goes into 64-bit bypassing the 32-bit. In theory, it should remove whole lot code, make it safer as well as faster. If rival AMD was to play along things could move much faster. Now don t get me wrong, 32-bit was good, but for it s time. I m sure at some point in time even 64-bit would have its demise, and we would jump to 128-bit. Of course, in reality we aren t anywhere close to even 48-bit, leave alone 64-bit. Superuser gives a good answer on that. We may be a decade or more before we exhaust that but for sure there will be need for better, faster hardware especially as we use more and more of AI for good and bad things. I am curious to see how it pans out and how it will affect (or not) FOSS gaming. FWIW, I used to peruse freegamer.blogspot.com which kinda ended in 2021 and now use Lee Reilly blog posts to know what is happening in github as far as FOSS games are concerned. There is also a whole thing about handhelds and gaming but that probably would require its own blog post or two. There are just too many while at the same time too few (legally purchasable in India) to have its own blog post, maybe sometime in Future. Best way to escape the world. Till later.

dd if=/dev/sda of=/dev/disk/by-id/usb0 status=progress

fdisk -l /dev/disk/by-id/usb0
fdisk -l /dev/sda

dd if=/dev/zero of=/dev/sda bs=1M count=42

# adduser cjac sudoers

# exit

$ sudo ls

$ sudo apt-get install virt-manager libvirt-daemon-driver-qemu qemu-system-x86

$ sudo qemu-img convert -O qcow2 \
/dev/disk/by-id/usb0 \
/var/lib/libvirt/images/windows.qcow2

sudo lvcreate /dev/vg00 -n windows -L 42G # or however large your drive was
sudo dd if=/dev/disk/by-id/usb0 of=/dev/vg00/windows status=progress

Goals Primarily I want to design a CO2 monitor which allows the majority of the production process to be outsourced. In particular, the PCB should be able to be assembled in an automated fashion (PCBA). As a secondary goal, I d like to improve the aesthetics of the monitor while retaining the unique feature of displaying clear visual indication of the current ventilation level through coloured lights. Overall, I ll consider the project successfull if I can achieve a visually attractive CO2 monitor which takes me less than 10 minutes per monitor to assemble/box/ship and whose production cost has the potential to be lower than the current model.

PCB

Schematic The existing CO2 monitor design provides a solid foundation but relies upon the ESP32 Devkit board, which is intended for evaluation purposes and is not well suited to automated assembly. Replacing this devkit board with the underlying ESP32 module is the major change needed to enable PCBA production, which then also requires moving the supporting electronics from the devkit board directly onto the primary PCB. The basic ESP32 chipset used in the devkit boards is no longer available as a discrete module suitable for placement directly onto a PCB which means the board will also have to be updated to use a more modern variant of the ESP32 chipset which is in active production such as the ESP32-S3. The ESP32-S3-WROOM1-N4 module is a very close match to the original devkit and will be suitable for this project. In addition to the change of ESP module, I made the following other changes to the components in use:

• Added an additional temperature/humidity sensor (SHT30). The current monitors take temperature/humidity measurements from the SCD40 chipset. These are primarily intended to help in the calculation of CO2 levels and rely on an offset being subtracted to account for the heat generated by the electronic components themselves. I ve found their accuracy to OK, but not perfect. SHT30 is a cheap part, so its addition to hopefully provide improved temperature/humidity measurement is an easy choice.
• Swapped to USB-C instead of USB-B for the power connector. USB-C is much more common than USB-B and is also smaller and not as tall off the board which provides more flexibility in the case design.

With major components selected the key task is to draw the schematic diagram describing how they electrically connect to each other, which includes all the supporting electronics (e.g. resistors, capacitors, etc) needed. I started out trying to use the EasyEDA/OSHWLab ecosystem thinking the tight integration with JLCPCB s assembly services would be a benefit, but the web interface was too clunky and limiting and I quickly got frustrated. KiCad proved to be a much more pleasant and capable tool for the job. The reference design in the ESP32 datasheet (p28) and USB-C power supply examples from blnlabs were particularly helpful alongside the KiCad documentation and the example of the existing monitor in completing this step (click the image to enlarge).

Layout The next step is to physically lay out where each component from the schematic will sit on the PCB itself. Obviously this requires first determining the overall size, shape and outline of the board and needs to occur in iteration with the intended design of the overall monitor, including the case, to ensure components like switches and USB sockets line up correctly. In addition to the requirements around the look and function of the case, the components themselves also have considerations that must be taken into account, including:

• For best WiFi reception, the ESP32 antenna should be at the top of the monitor and should not have PCB underneath it, or for a specified distance either side of it.
• The SHT30 temperature sensor should be as far from any heat generating components (e.g. the ESP32, BME680 and SCD40 modules) as possible and also considering that any generated heat will rise, as low on the monitor as possible.
• The sensors measuring the air (SCD40, BME680 and SHT30) must have good exposure to the air outside the case.

Taking all of these factors into account I ended up with a square PCB containing a cutout in the top right so that the ESP32 antenna can sit within the overall square outline while still meeting its design requirements. The SCD40 and BME680 sit in the top left corner, near the edges for good airflow and far away from the SHT30 temperature sensor in the bottom left corner. The LEDs I placed in a horizontal row across the center of the board, the LCD in the bottom right, a push button on the right-hand side and the USB-C socket in the center at the bottom. Once the components are placed, the next big task is to route the traces (aka wires) between the components on the board such that all the required electrical connections are made without any unintended connections (aka shorts) being created. This is a fun constraint solving/optimisation challenge and takes on an almost artistic aspect with other PCB designers often having strong opinions on which layout is best. The majority of the traces and routing for this board were able to be placed on the top layer of the PCB, but I also made use of the back layer for a few traces to help avoid conflicts and deal with places where different traces needed to cross each other. It s easy to see how this step would be much more challenging and time consuming on a larger and more complex PCB design. The final touches were to add some debugging breakouts for the serial and JTAG ports on the ESP32-S3 and a logo and various other helpful text on the silkscreen layer that will be printed on the PCB so it looks nice.

Production For assembly of the PCB, I went with JLCPCB based out of China. The trickiest part of the process was component selection and ensuring that the parts I had planned in the schematic were available. JLCPCB in conjunction with lcsc.com provides a basic and extended part library. If you use only basic parts you get quicker and cheaper assembly, while using extended parts bumps your order into a longer process with a small fee charged for each component on the board. Initially I spent a lot of time selecting components (particularly LEDs and switches) that were in the basic library before realising that the ESP32 modules are only available in the extended library! I think the lesson is that unless you re building the most trivial PCB with only passive components you will almost certainly end up in the advanced assembly process anyway, so trying to stay within the basic parts library is not worth the time. Unfortunately the SCD40 sensor, the most crucial part of the monitor, is not stocked at all by JLCPCB/LCSC! To work around this JLCPCB will maintain a personal component library for you when you ship components to them to for use in future orders. Given the extra logistical time and hassle of having to do this, combined with having a number of SCD40 components already on hand I decided to have the boards assembled without this component populated for the initial prototype run. This also had the benefit of lowering the risk if something went wrong as the cost of the SCD40 is greater than the cost of the PCB and all the other components combined! I found the kicad-jlcpcb-tools plugin for KiCad invaluable for keeping track of what part from lcsc.com I was planning to use for each component and generating the necessary output files for JLCPCB. The plugin allows you to store these mappings in your actual schematic which is very handy. The search interface it provides is fairly clunky and I found it was often easier to search for the part I needed on lcsc.com and then just copy the part number across into the plugin s search box rather than trying to search by name or component type. The LCD screen is the remaining component which is not easily assembled onto the PCB directly, but as you ll see next, this actually turned out to be OK as integrating the screen directly into the case makes the final assembly process smoother. The final surprise in the assembly process was the concept of edge rails, additional PCB material that is needed on either side of the board to help with feeding it through the assembly machine in the correct position. These can be added automatically by JLCPCB and have to be snapped off after the completed boards are received. I hadn t heard about these before and I was a little worried that they d interfere or get in the way of either the antenna cut-out at the top of the board, or the switch on the right hand side as it overhangs the edge so it can sit flush with the case. In the end there was no issue with the edge rails. The switch was placed hanging over them without issue and snapping them off once the boards arrived was a trivial 30s job using a vice to hold the edge rail and then gently tipping the board over until it snapped off - the interface between the board and the rails while solid looking has obviously been scored or perforated in some way during the production process so the edge breaks cleanly and smoothly. Magic! The process was amazingly quick with the completed PCBs (picture above) arriving within 7 days of the order being placed and looking amazing.

Case

Design I mocked up a very simple prototype of the case in FreeCAD during the PCB design process to help position and align the placement of the screen, switch and USB socket on the PCB as all three of these components interface directly with the edges of the case. Initially this design was similar to the current monitor design where the PCB (with lights and screen attached) sits in the bottom of the case, which has walls containing grilles for airflow and then a separate transparent perspex is screwed onto the top to complete the enclosure. As part of the aesthetic improvements for the new monitor I wanted to move away from a transparent front panel to something opaque but still translucent enough to allow the colour of the lights to show through. Without a transparent front panel the LCD also needs to be mounted directly into the case itself. The first few prototype iterations followed the design of the original CO2 monitor with a flat front panel that attaches to the rest of the case containing the PCB, but the new requirement to also attach the LCD to the front panel proved to make this unworkable. To stay in place the LCD has to be pushed onto mounting poles containing a catch mechanism which requires a moderate amount of force and applying that force to the LCD board when it is already connected to the PCB is essentially impossible. As a result I ended up completely flipping the design such that the front panel is a single piece of plastic that also encompasses the walls of the case and contains appropriate mounting stakes for both the screen and the main PCB. Getting to this design hugely simplified the assembly process. Starting with an empty case lying face down on a bench, the LCD screen is pushed onto the mounting poles and sits flush with the cover of the case - easily achieved without the main PCB yet in place. Next, the main PCB is gently lowered into the case facing downwards and sits on the mounting pole in each corner with the pins for the LCD just protruding through the appropriate holes in the PCB ready to be quickly soldered into place (this took significant iteration and tuning of dimensions/positioning to achieve!). Finally, a back panel can be attached which holds the PCB in place and uses cantilever snap joints to click on to the rest of the case. Overall the design is a huge improvement over the previous case which required screws and spacers to position the PCB and cover relative to the rest of the case, with the spacers and screws being particularly fiddly to work with. The major concern I had with the new design was that the mount to attach the monitor to the wall has moved from being attached to the main case and components directly to needing to be on the removable back panel - if the clips holding this panel to the case fail the core part of the monitor will fall off the wall which would not be good. To guard against this I ve doubled the size and number of clips at the top of the case (which bears the weight) and the result seems very robust in my testing. To completely assemble a monitor, including the soldering step takes me about 2-3 minutes individually, and would be even quicker if working in batches.

Production Given the number of design/testing iterations required to fine tune the case I chose not to outsource case production for now and used my 3D printer to produce them. I ve successfully used JLCPCB s 3D printing service for the previous case design, so I m confident that getting sufficient cases printed from JLCPCB or another supplier will not be an issue now that the design is finalised. I tried a variety of filament colours, but settled on a transparent filament which once combined in the necessary layers to form the case is not actually transparent like perspex is, but provides a nice translucent medium which achieves the goal of having the light colour visible without exposing all of the circuit board detail. There s room for future improvement in the positioning of the LEDs on the circuit board to provide a more even distribution of light across the case but overall I really like the way the completed monitor ends up looking.

Evaluation Building this monitor has been a really fun project, both in seeing something progress from an idea, to plans on a screen to a nice physical thing on my wall, but also in learning and developing a bunch of new skills in PCB design, assembly and 3D design. The goal of having a CO2 monitor which I can outsource the vast majority of production of is as close to being met as I think is possible without undertaking the final proof of placing a large order. I ve satisfied myself that each step is feasible and that the final assembly process is quick, easy and well below the level of effort and time it was taking me to produce the original monitors. Cost wise it s also a huge win, primarily in terms of the time taken, but also in the raw components - currently the five prototypes I ordered and built are on par with the component cost of the original CO2 monitor, but this will drop further with larger orders due to price breaks and amortisation of the setup and shipping expenses across more monitors. This project has also given me a much better appreciation for how much I m only just scratching the surface of the potential complexities and challenges in producing a hardware product of this type. I m reasonably confident I could successfully produce a few hundred and maybe even a few thousand monitors using this approach, but it s also clear that getting beyond that point is and would be a whole further level of effort and learning. Hardware is hard work. That s not news to anyone, including me, but there is something to be said for experiencing the process first hand to make the reality of what s required real. The PCB and case designs are both shared and can be found at https://github.com/co2monnz/co2monitor-pcb and https://github.com/co2monnz/cad, feedback and suggestions welcome!

"Zoology, eh? That's a big word, isn't it." "No, actually it isn't," said Tiffany. "Patronizing is a big word. Zoology is really quite short."

Crossing the ocean of stars we leave our home behind us.
We are the spears cast at the furious heaven
And we will burn one by one into ashes
As with the last sparks we vanish.
This memory we carry to our own death which awaits us
And from which none of us will return.
Do not forget. Goodbye forever.

git-annex allows managing large files with git, without storing the file contents in git. It can sync, backup, and archive your data, offline and online. Checksums and encryption keep your data safe and secure. Bring the power and distributed nature of git to bear on your large files with git-annex.

• I want exactly 1 copy of every file to exist within the set #1 of backup drives. Here s a drive in that set; copy to it whatever needs to be copied to satisfy that requirement.
• Now I have another set of backup drives. Periodically I will swap sets offsite. Copy whatever is needed to this drive in the second set, making sure that there is 1 copy of every file within this set as well, regardless of what s in the first set.
• Here s a directory I want to use to track the status of everything else. I don t want any copies at all here.

• git-annex doesn t really preserve POSIX attributes; for instance, permissions, symlink destinations, and timestamps are all not preserved. Of these, timestamps are the most important for my particular use case.
• If your data set to archive contains Git repositories itself, these will not be included.

• There is a source of data that lives outside git-annex. I'll call this $SOURCEDIR.
• I'm going to name the directories holding my data $REPONAME.
• There will be a "coordination" git-annex repo. It will hold metadata only, and no data. This will let us track where things live. I'll call it $METAREPO.
• There will be drives. For this example, I'll call their mountpoints $DRIVE01 and $DRIVE02. For easy demonstration purposes, I used a ZFS dataset with a refquota set (to observe the size handling), but I could have as easily used a LVM volume, btrfs dataset, loopback filesystem, or USB drive. For optical discs, this would be a staging area or a UDF filesystem.

192.168.1.33 octoprint.local

podman run --rm -d --name octoprint \
        ...
        --network bridge_local --ip 192.168.1.33 \
        octoprint/octoprint

Demonetization 2.0 Few days back, India announced demonetization 2.0. Surprised, don t be. Apparently, INR 2k/- is being used for corruption and Mr. Modi is unhappy about it. He actually didn t like the INR 2k/- note but was told that it was needed, who told him we are unaware to date. At that time the RBI Governor was Mr. Urjit Patel who didn t say about INR 2k/- he had said that INR 1k/- note redesigned would come in the market. That has yet to happen. What has happened is that just like INR 500/- and INR 1k/- note is concerned, RBI will no longer honor the INR 2k/- note. Obviously, this has made our neighbors angry, namely Nepal, Sri Lanka, Bhutan etc. who do some trading with us. 2 Deccan herald columns share the limelight on it. Apparently, India wants to be the world s currency reserve but doesn t want to play by the rules for everyone else. It was pointed out that both the U.S. and Singapore had retired their currencies but they will honor that promise even today. The Singapore example being a bit closer (as it s in Asia) is perhaps a bit more relevant than the U.S. one. Singapore retired the SGD $10,000 as of 2014 but even in 2022, it remains as legal tender. They also retired the SGD $1,000 in 2020 but still remains legal tender.

So let s have a fictitious example to illustrate what is meant by what Singapore has done. Let s say I go to Singapore, rent a flat, and find a $1000 note in that house somewhere. Both practically and theoretically, I could go down to any of the banks, get the amount transferred to my wallet, bank account etc. and nobody will question. Because they have promised the same. Interestingly, the Singapore Dollar has been pretty resilient against the USD for quite a number of years vis-a-vis other Asian currencies. Most of the INR 2k/- notes were also found and exchanged in Gujarat in just a few days (The PM and HM s state.). I am sure you are looking into the mental gymnastics that the RW indulge in :(. What is sadder that most of the people who try to defend can t make sense one way or the other and start to name-call and get personal as they have nothing else

Disability questions dropped in NHFS-6 Just came to know today that in the upcoming National Family Health Survey-6 disability questions are being dropped. Why is this important. To put it simply, if you don t have numbers, you won t and can t make policies for them. India is one of the worst countries to live if you are disabled. The easiest way to share to draw attention is most Railway platforms are not at level with people. Just as Mick Lynch shares in the UK, the same is pretty much true for India too. Meanwhile in Europe, they do make an effort to be level so even disabled people have some dignity. If your public transport is sorted, then people would want much more and you will be obligated to provide for them as they are citizens. Here, we have had many reports of women being sexually molested when being transferred from platform to coach irrespective of their age or whatnot The main takeaway is if you do not have their voice, you won t make policies for them. They won t go away but you will make life hell for them. One thing to keep in mind that most people assume that most people are disabled from birth. This may or may not be true. For e.g. in the above triple Railways accidents, there are bound to be disabled people or newly disabled people who were healthy before the accident. The most common accident is road accidents, some involving pedestrians and vehicles or both, the easiest is Ministry of Road Transport data that says 4,00,000 people sustained injuries in 2021 alone in road mishaps. And this is in a country where even accidents are highly under-reported, for more than one reason. The biggest reason especially in 2 and 4 wheeler is the increased premium they would have to pay if in an accident, so they usually compromise with the other and pay off the Traffic Inspector. Sadly, I haven t read a new book, although there are a few books I m looking forward to have. People living in India and neighbors please be careful as more heat waves are expected. Till later.