Antoine Beaupr : A more nuanced view of LLMs
Also in this series:After ranting and railing about LLMs or "AI" as the optimists (or accelerationists?) call it, I figured it might be important to be a little more honest about my use of LLMs and how I think about it more practically in the world.
The Debian vote context
This is not a coming out. I am not using LLMs on a daily basis, and
this blog is, again, written out of my cold dead hands in a dying
world, with over-engineered hardware and (to a certain extent, hi
Emacs!) software, powered by 100% green energy built on stolen land.
There is a vote going on in Debian. If you're unfamiliar with it,
you can catch up at LWN. So far I've essentially said "LLM is
bad" which is not a very balanced or useful opinion. Obviously, people
are using LLMs, sometimes unknowing or unwillingly, and we need to
take that into account. Furthermore, there has been many different
blog posts on Debian planet about this. Some that I found
balanced, good summaries, even if I didn't fully agree with
them, at least some did the basic civil service of being
short. But others were just not only Wrong but also so long
that I couldn't finish that I just had to write something.1
This is not an explanation of the ballots, nor how I will vote. This
vote is Debian's failure of framing that debate in a reasonable way:
we have 8 options on the ballot with many duplicates. We have failed
to do the hard work of summarizing and aggregating options into a
meaningful set. I doubt the final vote will represent a readable
position we can rally around.
I have not read the two months of debates on the topic
either. Normally, before voting, I take a cursory look at the debate
to see points of view I might have missed. But in this case, it will
just make me sad, add noise, and I'm already pretty sure on where I
stand on this.
So let me describe how I use LLMs and how I think they fit in our
work, as computer engineers and hobbyists.
My LLM use
Debian Packaging
An astute reader has pointed out that I maintain a package in
Debian made to use Anthropic. It's actually multiple packages:
llm: a CLI utility and Python library for interacting with
Large Language Models, with OpenAI as its default API backendllm-anthropic: a plugin for llm which allows me to talk to
Anthropic's API instead of OpenAIanthropic-sdk-python: the SDK llm-anthropic requires to do
its work
As I previously explained in response, I am not entirely
comfortable with this work: it's a compromise. In fact, I first
uploaded llm to the contrib section of Debian, where we keep
software that depends on other non-free software, but I was told that,
since yt-dlp was in main, llm belonged there as well.
So I moved it to main, alongside similarly controversial tools
like llama.cpp or the python-openai library.
OpenAI and Anthropic usage
An important part of my work is technology watch. I keep tabs on
thousands of (new and old) software projects, follow news, and
generally try to keep my skills up to date. It's a pretty impossible
race, especially as I grow older, but I still think I'm doing the
right choices in my job.
Testing large language models is part of that work. At first, I was
using ChatGPT's web interface, but it was annoying to copy-paste
things into a browser, so I looked for different interfaces.
For a while I tried gptel, a "simple, extensible LLM client for
Emacs" but I found it kind of terrifying. Giving a LLM control over an
Emacs buffer seems like a security nightmare, so I stopped doing
that.
So I use the llm command-line tool to talk to Anthropic's API. I
started that in the summer of 2025, when I bought 20$USD of API
credits. Before that, I paid for a ChatGPT subscription and then
OpenAI credits, which expired and sent me over to Anthropic, which
seemed then to have better ethics.
As it turns out, Anthropic is also happy to work for the US military
(which is a big red line for me). Anthropic also won't let you talk
about the genocide in Gaza, it is destroying physical books,
and is blackmailing us to use their product for security
coverage.
Needless to say, Anthropic and "Claude" are not my friends, but they
seem like the lesser evil in current "frontier models". So I have
renewed, a couple of weeks ago, another 20$USD of API credits with
Anthropic.
Actual prompts and responses
So what does 20$ give you at Anthropic anyways? What am I using LLMs
for and how?
The neat thing with llm is that everything is logged in a sqlite
database, so there are some answers that are easy to get:
> llm logs status
Logging is ON for all prompts
Found log database at /home/anarcat/.config/io.datasette.llm/logs.db
Number of threads logged: 7
Number of turns logged: 12
Number of legacy conversations: 543
Number of legacy responses: 970
Database file size: 9.61MB
That is 10MB of logs, with about a thousand prompts.
My logs go back to 2024-03-07, a little over two years ago, and
include a mix of Anthropic and OpenAI responses. I used it more in
2024 than 2025, and if the trend continues, I will have used it less
in 2026 again:
> llm logs list -n 0 --json jq -r .[].datetime_utc sed 's/-.*//' sort uniq -c
527 2024
357 2025
98 2026
It looks like about 10 prompts per month right now, down from a peak
of about 60 per month in 2024. It's pretty difficult to analyze those
actual logs to get more patterns and I won't run the prompts through a
model again to process them.
How I'm using models now
At first, I was using it partly for benchmarking model's capabilities,
like Simon Willison does with his pelicans, clearly not trusting
its output. But I was impressed by the capacities of the Claude Opus
4.5 model when it wrote this script in January. Impressed, but
also scared: it's the first time I felt I could delegate the entirety
of my programming to a model. Just run the code, if it works, it
works, right?
So what do I use it now? As an example, here are the 10 last prompts
in my history:
- there is now Claude 5, and a fable model, maybe you know about it?
- impress me
- not impressive, i already know all of this
- chat
- in postfix, i have a 300k mailing that happens regularly here. normally, it delivers within about...
- is there a way i could have drained the maildrop queue faster without removing the milter?
- the problem was that rspamd was timing out on the FUZZY_CALLBACK check. how do i disable that?
- how do i disable all spam checks? i just want rspamd to add dkim signatures
- how do the default_destination_concurrency_limit and initial_destination_concurrency settings int...
- mic check
The first one was me trying to confirm which model I am using, which
is not always obvious when going through the whole llm stack I've
been using. The following two are an attempt at seeing what the model
is capable of and I was "not impressed", to which Claude answered that
I have a "high bar", which, fair enough.
The chat is me failing to use a command line, which shows that
perhaps I need to readjust that "high bar", again.
The next five are a rather embarrassing debacle in a large Postfix
mailing that went sideways, and where I couldn't find an actual
Postfix expert of my level to help. The fabled Claude Fable 5 answered
rather correctly, but dangerously, that I could empty the queue by
disabling the non_smtpd_milters. What Fable (and myself) did not
realize is that the milter was also adding DKIM signatures, so while the
mailing was expedited, it was done without those precious signatures,
which got us promptly blocked at Gmail. We have recovered since, and,
thanks to the model and reading the Postfix manual for the
hundredth time, that pickup(8) is single-threaded and that we
needed to review the architecture of that mailing (and our spam
filters) a bit. Many tickets ensued.
The last one is a test I did to make sure my last uploads of
llm-anthropic and its dependency worked correctly.
Note that the above excludes 5 questions I asked Anthropic while
writing this article, where I asked for synonyms and "what nanometer
scale are arduino processors built from? how is an arduino CPU
printed?", a question which Wikipedia furiously evades providing a
good answer.
Those prompts are pretty typical of my LLM use: I'm testing the models
to see if they work at all, but also, out of desperation, I fire off a
prompt after I fire off questions to colleagues or search engines (in
that order). It's often weird edge cases like the Prometheus query
language, Python's matplotlib, LaTeX, Elisp, optimizations, and so on.
I use models for translation a lot. Being fully bilingual, it is
common for me to think of a word in French or English and fail to find
exactly the right word for that in the other language. Models help
with that, and are also useful to find synonyms. Those are low-token
uses that seem pretty innocuous to me, but I realize the irony of this
after writing about the tower of
Babel.
What I am not using models for
I am not using models to write prose.
I am not using models to read prose. If it's generated with LLMs, I
stop reading.
I am not using models to write code, with the exception of that single
Python script above.
I am generally not using models to review code, with exceptions. If
I get stuck on a hard problem, I might feed a piece of code to the
model. I repeatedly fed asncounter into Claude to try to fix a
performance regression I had introduced. It found micro-optimizations
that taught me a thing or two about Python's internal implementations,
but overall, it was mostly a waste of time. This was in June 2025, so
perhaps now models would fare better. I have not tried again.
I am not using LLMs to do Debian packaging. When I can, I manually
review the diffs of packages I upload into Debian, still, by hand.
I do this for the reasons outlined in The Four Horsemen of the LLM
Apocalypse, because I refuse to be
complicit in the:
- aggressive and illegal scraping of the servers I steward
- world-wide computer hardware shortage (making it, by the way,
nearly impossible to run presumably clean local models) and the
attack on our job conditions (also discussed in
The people vs the AI overlords)
- death of copyright and free software
- complication and enshifitication of everything, and the
destruction of our communities
- the imperialist Nerd Reich that wants to take over the world
Like I reluctantly use Intel computers, I do fire off a prompt. But
I still hold on to the dream that we can build communities of
practice that hold human knowledge collectively and not offload
that as a utility to some megalomaniac billionaire.
Their LLM use I am forced into
So that's me. Clearly, I'm going against the grain here. Everywhere I
look, I see LLM-generated code and projects. Slop and botnets have
flooded the web.
I use Wadamesh, clearly vibe-coded, because it's the best
graphical interface for MeshCore that runs on portable devices. I wish
it was made by a human, in a community I could participate in, but it
isn't, and I don't.
I package the above llm toolset, which is more and more
vibe-coded, but I still review the diffs. And I have to say: I
trust Simon here. The code is verbose as hell, feels overengineered,
and llm feels slow, but it generally works, and Simon is still at
the gate.
The Anthropic SDK is another thing entirely. The 0.91.0 to 0.120
upload, for example, was nuts:
806 files changed, 72281 insertions(+), 1478 deletions(-)
I explicitly did not review that entire diff. It feels like there's a
lot of garbage there to just have a shim between a proprietary API and
Python. But this is the hand I've been dealt.
Larger projects LLM use
LLMs are being used in the Linux kernel, Firefox, rsync, Rust, and
other places. I don't feel good about this, particularly in Rust, but
they at least made a decent policy. I am glad GCC made a policy
against LLM contributions and I support the human Emacs
project.
We need to have a set of foundational tools that are "clean" in the
sense that they are built upon a community of people that understand
how they are built.
Maybe that's naive or even impossible. The Linux kernel and GCC, in
particular, are massive projects that have long grown past the scale
of a single person's understanding. But the theory was that a
community of humans can understand collectively.
Now we seem to be throwing up our hands and giving up on
that community. That LLMs will just fix the problem, whatever it
is. But we're all just one rug pull away from being completely
incapable of managing those projects. The argument there is that we'll
just switch to local models, but no one is actually doing that.
All I see is people use local models as a corner case
(for privacy) or as in theory, but in reality, everyone uses the
centralized frontier models right now. We just can't fallback.
We're in the same situation we were, a decade or two ago, when
Microsoft decided it would kill free office alternatives by making
Office free for non-profits. It worked: thousands, if not millions of
schools, community groups and individuals stopped looking for
alternatives (including free software but also "piracy") for Office
and embraced what seemed like a generous offer.
Now Microsoft pulled the plug and Over 170,000 Nonprofits Lost All
Their Data.
I'm afraid the rug pull on LLMs will be much worse: never mind that
Linus won't be able to use his tireless helper to fix obscure kernel
bugs; we're looking at a collapse of the economy so large that we are
already talking about bailing out the companies responsible.
In a sense, the most striking thing about the Debian vote is it has
actually no option to completely refuse upstream LLM contributions. It
seems the community has taken it for granted that it's now impossible
to build Debian entirely without LLMs. We lost the battle even without
a fight, it seems.
A plea for small
If it has really become impossible for us to manage the complexity we
have built, maybe it's time to stop and think about what we're doing
in the first place. We're struggling to even bootstrap our
current toolchain!
This is one of the things I like the most about working on the mesh:
it's low tech, small Arduino devices that is built with decades-old
semiconductor processes that is understandable by human
beings.
Maybe the answer lies more in single-purpose devices like those
communicators and simpler multi-purpose computers than what we have
now, which is what the permacomputing movement is about.
Small is beautiful, let's scale it down.
Debian Packaging
An astute reader has pointed out that I maintain a package in
Debian made to use Anthropic. It's actually multiple packages:
llm: a CLI utility and Python library for interacting with
Large Language Models, with OpenAI as its default API backendllm-anthropic: a plugin for llm which allows me to talk to
Anthropic's API instead of OpenAIanthropic-sdk-python: the SDK llm-anthropic requires to do
its work
As I previously explained in response, I am not entirely
comfortable with this work: it's a compromise. In fact, I first
uploaded llm to the contrib section of Debian, where we keep
software that depends on other non-free software, but I was told that,
since yt-dlp was in main, llm belonged there as well.
So I moved it to main, alongside similarly controversial tools
like llama.cpp or the python-openai library.
OpenAI and Anthropic usage
An important part of my work is technology watch. I keep tabs on
thousands of (new and old) software projects, follow news, and
generally try to keep my skills up to date. It's a pretty impossible
race, especially as I grow older, but I still think I'm doing the
right choices in my job.
Testing large language models is part of that work. At first, I was
using ChatGPT's web interface, but it was annoying to copy-paste
things into a browser, so I looked for different interfaces.
For a while I tried gptel, a "simple, extensible LLM client for
Emacs" but I found it kind of terrifying. Giving a LLM control over an
Emacs buffer seems like a security nightmare, so I stopped doing
that.
So I use the llm command-line tool to talk to Anthropic's API. I
started that in the summer of 2025, when I bought 20$USD of API
credits. Before that, I paid for a ChatGPT subscription and then
OpenAI credits, which expired and sent me over to Anthropic, which
seemed then to have better ethics.
As it turns out, Anthropic is also happy to work for the US military
(which is a big red line for me). Anthropic also won't let you talk
about the genocide in Gaza, it is destroying physical books,
and is blackmailing us to use their product for security
coverage.
Needless to say, Anthropic and "Claude" are not my friends, but they
seem like the lesser evil in current "frontier models". So I have
renewed, a couple of weeks ago, another 20$USD of API credits with
Anthropic.
Actual prompts and responses
So what does 20$ give you at Anthropic anyways? What am I using LLMs
for and how?
The neat thing with llm is that everything is logged in a sqlite
database, so there are some answers that are easy to get:
> llm logs status
Logging is ON for all prompts
Found log database at /home/anarcat/.config/io.datasette.llm/logs.db
Number of threads logged: 7
Number of turns logged: 12
Number of legacy conversations: 543
Number of legacy responses: 970
Database file size: 9.61MB
That is 10MB of logs, with about a thousand prompts.
My logs go back to 2024-03-07, a little over two years ago, and
include a mix of Anthropic and OpenAI responses. I used it more in
2024 than 2025, and if the trend continues, I will have used it less
in 2026 again:
> llm logs list -n 0 --json jq -r .[].datetime_utc sed 's/-.*//' sort uniq -c
527 2024
357 2025
98 2026
It looks like about 10 prompts per month right now, down from a peak
of about 60 per month in 2024. It's pretty difficult to analyze those
actual logs to get more patterns and I won't run the prompts through a
model again to process them.
How I'm using models now
At first, I was using it partly for benchmarking model's capabilities,
like Simon Willison does with his pelicans, clearly not trusting
its output. But I was impressed by the capacities of the Claude Opus
4.5 model when it wrote this script in January. Impressed, but
also scared: it's the first time I felt I could delegate the entirety
of my programming to a model. Just run the code, if it works, it
works, right?
So what do I use it now? As an example, here are the 10 last prompts
in my history:
- there is now Claude 5, and a fable model, maybe you know about it?
- impress me
- not impressive, i already know all of this
- chat
- in postfix, i have a 300k mailing that happens regularly here. normally, it delivers within about...
- is there a way i could have drained the maildrop queue faster without removing the milter?
- the problem was that rspamd was timing out on the FUZZY_CALLBACK check. how do i disable that?
- how do i disable all spam checks? i just want rspamd to add dkim signatures
- how do the default_destination_concurrency_limit and initial_destination_concurrency settings int...
- mic check
The first one was me trying to confirm which model I am using, which
is not always obvious when going through the whole llm stack I've
been using. The following two are an attempt at seeing what the model
is capable of and I was "not impressed", to which Claude answered that
I have a "high bar", which, fair enough.
The chat is me failing to use a command line, which shows that
perhaps I need to readjust that "high bar", again.
The next five are a rather embarrassing debacle in a large Postfix
mailing that went sideways, and where I couldn't find an actual
Postfix expert of my level to help. The fabled Claude Fable 5 answered
rather correctly, but dangerously, that I could empty the queue by
disabling the non_smtpd_milters. What Fable (and myself) did not
realize is that the milter was also adding DKIM signatures, so while the
mailing was expedited, it was done without those precious signatures,
which got us promptly blocked at Gmail. We have recovered since, and,
thanks to the model and reading the Postfix manual for the
hundredth time, that pickup(8) is single-threaded and that we
needed to review the architecture of that mailing (and our spam
filters) a bit. Many tickets ensued.
The last one is a test I did to make sure my last uploads of
llm-anthropic and its dependency worked correctly.
Note that the above excludes 5 questions I asked Anthropic while
writing this article, where I asked for synonyms and "what nanometer
scale are arduino processors built from? how is an arduino CPU
printed?", a question which Wikipedia furiously evades providing a
good answer.
Those prompts are pretty typical of my LLM use: I'm testing the models
to see if they work at all, but also, out of desperation, I fire off a
prompt after I fire off questions to colleagues or search engines (in
that order). It's often weird edge cases like the Prometheus query
language, Python's matplotlib, LaTeX, Elisp, optimizations, and so on.
I use models for translation a lot. Being fully bilingual, it is
common for me to think of a word in French or English and fail to find
exactly the right word for that in the other language. Models help
with that, and are also useful to find synonyms. Those are low-token
uses that seem pretty innocuous to me, but I realize the irony of this
after writing about the tower of
Babel.
What I am not using models for
I am not using models to write prose.
I am not using models to read prose. If it's generated with LLMs, I
stop reading.
I am not using models to write code, with the exception of that single
Python script above.
I am generally not using models to review code, with exceptions. If
I get stuck on a hard problem, I might feed a piece of code to the
model. I repeatedly fed asncounter into Claude to try to fix a
performance regression I had introduced. It found micro-optimizations
that taught me a thing or two about Python's internal implementations,
but overall, it was mostly a waste of time. This was in June 2025, so
perhaps now models would fare better. I have not tried again.
I am not using LLMs to do Debian packaging. When I can, I manually
review the diffs of packages I upload into Debian, still, by hand.
I do this for the reasons outlined in The Four Horsemen of the LLM
Apocalypse, because I refuse to be
complicit in the:
- aggressive and illegal scraping of the servers I steward
- world-wide computer hardware shortage (making it, by the way,
nearly impossible to run presumably clean local models) and the
attack on our job conditions (also discussed in
The people vs the AI overlords)
- death of copyright and free software
- complication and enshifitication of everything, and the
destruction of our communities
- the imperialist Nerd Reich that wants to take over the world
Like I reluctantly use Intel computers, I do fire off a prompt. But
I still hold on to the dream that we can build communities of
practice that hold human knowledge collectively and not offload
that as a utility to some megalomaniac billionaire.
Their LLM use I am forced into
So that's me. Clearly, I'm going against the grain here. Everywhere I
look, I see LLM-generated code and projects. Slop and botnets have
flooded the web.
I use Wadamesh, clearly vibe-coded, because it's the best
graphical interface for MeshCore that runs on portable devices. I wish
it was made by a human, in a community I could participate in, but it
isn't, and I don't.
I package the above llm toolset, which is more and more
vibe-coded, but I still review the diffs. And I have to say: I
trust Simon here. The code is verbose as hell, feels overengineered,
and llm feels slow, but it generally works, and Simon is still at
the gate.
The Anthropic SDK is another thing entirely. The 0.91.0 to 0.120
upload, for example, was nuts:
806 files changed, 72281 insertions(+), 1478 deletions(-)
I explicitly did not review that entire diff. It feels like there's a
lot of garbage there to just have a shim between a proprietary API and
Python. But this is the hand I've been dealt.
Larger projects LLM use
LLMs are being used in the Linux kernel, Firefox, rsync, Rust, and
other places. I don't feel good about this, particularly in Rust, but
they at least made a decent policy. I am glad GCC made a policy
against LLM contributions and I support the human Emacs
project.
We need to have a set of foundational tools that are "clean" in the
sense that they are built upon a community of people that understand
how they are built.
Maybe that's naive or even impossible. The Linux kernel and GCC, in
particular, are massive projects that have long grown past the scale
of a single person's understanding. But the theory was that a
community of humans can understand collectively.
Now we seem to be throwing up our hands and giving up on
that community. That LLMs will just fix the problem, whatever it
is. But we're all just one rug pull away from being completely
incapable of managing those projects. The argument there is that we'll
just switch to local models, but no one is actually doing that.
All I see is people use local models as a corner case
(for privacy) or as in theory, but in reality, everyone uses the
centralized frontier models right now. We just can't fallback.
We're in the same situation we were, a decade or two ago, when
Microsoft decided it would kill free office alternatives by making
Office free for non-profits. It worked: thousands, if not millions of
schools, community groups and individuals stopped looking for
alternatives (including free software but also "piracy") for Office
and embraced what seemed like a generous offer.
Now Microsoft pulled the plug and Over 170,000 Nonprofits Lost All
Their Data.
I'm afraid the rug pull on LLMs will be much worse: never mind that
Linus won't be able to use his tireless helper to fix obscure kernel
bugs; we're looking at a collapse of the economy so large that we are
already talking about bailing out the companies responsible.
In a sense, the most striking thing about the Debian vote is it has
actually no option to completely refuse upstream LLM contributions. It
seems the community has taken it for granted that it's now impossible
to build Debian entirely without LLMs. We lost the battle even without
a fight, it seems.
A plea for small
If it has really become impossible for us to manage the complexity we
have built, maybe it's time to stop and think about what we're doing
in the first place. We're struggling to even bootstrap our
current toolchain!
This is one of the things I like the most about working on the mesh:
it's low tech, small Arduino devices that is built with decades-old
semiconductor processes that is understandable by human
beings.
Maybe the answer lies more in single-purpose devices like those
communicators and simpler multi-purpose computers than what we have
now, which is what the permacomputing movement is about.
Small is beautiful, let's scale it down.
llm: a CLI utility and Python library for interacting with
Large Language Models, with OpenAI as its default API backendllm-anthropic: a plugin for llm which allows me to talk to
Anthropic's API instead of OpenAIanthropic-sdk-python: the SDK llm-anthropic requires to do
its workgptel, a "simple, extensible LLM client for
Emacs" but I found it kind of terrifying. Giving a LLM control over an
Emacs buffer seems like a security nightmare, so I stopped doing
that.
So I use the llm command-line tool to talk to Anthropic's API. I
started that in the summer of 2025, when I bought 20$USD of API
credits. Before that, I paid for a ChatGPT subscription and then
OpenAI credits, which expired and sent me over to Anthropic, which
seemed then to have better ethics.
As it turns out, Anthropic is also happy to work for the US military
(which is a big red line for me). Anthropic also won't let you talk
about the genocide in Gaza, it is destroying physical books,
and is blackmailing us to use their product for security
coverage.
Needless to say, Anthropic and "Claude" are not my friends, but they
seem like the lesser evil in current "frontier models". So I have
renewed, a couple of weeks ago, another 20$USD of API credits with
Anthropic.
Actual prompts and responses
So what does 20$ give you at Anthropic anyways? What am I using LLMs
for and how?
The neat thing with llm is that everything is logged in a sqlite
database, so there are some answers that are easy to get:
> llm logs status
Logging is ON for all prompts
Found log database at /home/anarcat/.config/io.datasette.llm/logs.db
Number of threads logged: 7
Number of turns logged: 12
Number of legacy conversations: 543
Number of legacy responses: 970
Database file size: 9.61MB
That is 10MB of logs, with about a thousand prompts.
My logs go back to 2024-03-07, a little over two years ago, and
include a mix of Anthropic and OpenAI responses. I used it more in
2024 than 2025, and if the trend continues, I will have used it less
in 2026 again:
> llm logs list -n 0 --json jq -r .[].datetime_utc sed 's/-.*//' sort uniq -c
527 2024
357 2025
98 2026
It looks like about 10 prompts per month right now, down from a peak
of about 60 per month in 2024. It's pretty difficult to analyze those
actual logs to get more patterns and I won't run the prompts through a
model again to process them.
How I'm using models now
At first, I was using it partly for benchmarking model's capabilities,
like Simon Willison does with his pelicans, clearly not trusting
its output. But I was impressed by the capacities of the Claude Opus
4.5 model when it wrote this script in January. Impressed, but
also scared: it's the first time I felt I could delegate the entirety
of my programming to a model. Just run the code, if it works, it
works, right?
So what do I use it now? As an example, here are the 10 last prompts
in my history:
- there is now Claude 5, and a fable model, maybe you know about it?
- impress me
- not impressive, i already know all of this
- chat
- in postfix, i have a 300k mailing that happens regularly here. normally, it delivers within about...
- is there a way i could have drained the maildrop queue faster without removing the milter?
- the problem was that rspamd was timing out on the FUZZY_CALLBACK check. how do i disable that?
- how do i disable all spam checks? i just want rspamd to add dkim signatures
- how do the default_destination_concurrency_limit and initial_destination_concurrency settings int...
- mic check
The first one was me trying to confirm which model I am using, which
is not always obvious when going through the whole llm stack I've
been using. The following two are an attempt at seeing what the model
is capable of and I was "not impressed", to which Claude answered that
I have a "high bar", which, fair enough.
The chat is me failing to use a command line, which shows that
perhaps I need to readjust that "high bar", again.
The next five are a rather embarrassing debacle in a large Postfix
mailing that went sideways, and where I couldn't find an actual
Postfix expert of my level to help. The fabled Claude Fable 5 answered
rather correctly, but dangerously, that I could empty the queue by
disabling the non_smtpd_milters. What Fable (and myself) did not
realize is that the milter was also adding DKIM signatures, so while the
mailing was expedited, it was done without those precious signatures,
which got us promptly blocked at Gmail. We have recovered since, and,
thanks to the model and reading the Postfix manual for the
hundredth time, that pickup(8) is single-threaded and that we
needed to review the architecture of that mailing (and our spam
filters) a bit. Many tickets ensued.
The last one is a test I did to make sure my last uploads of
llm-anthropic and its dependency worked correctly.
Note that the above excludes 5 questions I asked Anthropic while
writing this article, where I asked for synonyms and "what nanometer
scale are arduino processors built from? how is an arduino CPU
printed?", a question which Wikipedia furiously evades providing a
good answer.
Those prompts are pretty typical of my LLM use: I'm testing the models
to see if they work at all, but also, out of desperation, I fire off a
prompt after I fire off questions to colleagues or search engines (in
that order). It's often weird edge cases like the Prometheus query
language, Python's matplotlib, LaTeX, Elisp, optimizations, and so on.
I use models for translation a lot. Being fully bilingual, it is
common for me to think of a word in French or English and fail to find
exactly the right word for that in the other language. Models help
with that, and are also useful to find synonyms. Those are low-token
uses that seem pretty innocuous to me, but I realize the irony of this
after writing about the tower of
Babel.
What I am not using models for
I am not using models to write prose.
I am not using models to read prose. If it's generated with LLMs, I
stop reading.
I am not using models to write code, with the exception of that single
Python script above.
I am generally not using models to review code, with exceptions. If
I get stuck on a hard problem, I might feed a piece of code to the
model. I repeatedly fed asncounter into Claude to try to fix a
performance regression I had introduced. It found micro-optimizations
that taught me a thing or two about Python's internal implementations,
but overall, it was mostly a waste of time. This was in June 2025, so
perhaps now models would fare better. I have not tried again.
I am not using LLMs to do Debian packaging. When I can, I manually
review the diffs of packages I upload into Debian, still, by hand.
I do this for the reasons outlined in The Four Horsemen of the LLM
Apocalypse, because I refuse to be
complicit in the:
- aggressive and illegal scraping of the servers I steward
- world-wide computer hardware shortage (making it, by the way,
nearly impossible to run presumably clean local models) and the
attack on our job conditions (also discussed in
The people vs the AI overlords)
- death of copyright and free software
- complication and enshifitication of everything, and the
destruction of our communities
- the imperialist Nerd Reich that wants to take over the world
Like I reluctantly use Intel computers, I do fire off a prompt. But
I still hold on to the dream that we can build communities of
practice that hold human knowledge collectively and not offload
that as a utility to some megalomaniac billionaire.
Their LLM use I am forced into
So that's me. Clearly, I'm going against the grain here. Everywhere I
look, I see LLM-generated code and projects. Slop and botnets have
flooded the web.
I use Wadamesh, clearly vibe-coded, because it's the best
graphical interface for MeshCore that runs on portable devices. I wish
it was made by a human, in a community I could participate in, but it
isn't, and I don't.
I package the above llm toolset, which is more and more
vibe-coded, but I still review the diffs. And I have to say: I
trust Simon here. The code is verbose as hell, feels overengineered,
and llm feels slow, but it generally works, and Simon is still at
the gate.
The Anthropic SDK is another thing entirely. The 0.91.0 to 0.120
upload, for example, was nuts:
806 files changed, 72281 insertions(+), 1478 deletions(-)
I explicitly did not review that entire diff. It feels like there's a
lot of garbage there to just have a shim between a proprietary API and
Python. But this is the hand I've been dealt.
Larger projects LLM use
LLMs are being used in the Linux kernel, Firefox, rsync, Rust, and
other places. I don't feel good about this, particularly in Rust, but
they at least made a decent policy. I am glad GCC made a policy
against LLM contributions and I support the human Emacs
project.
We need to have a set of foundational tools that are "clean" in the
sense that they are built upon a community of people that understand
how they are built.
Maybe that's naive or even impossible. The Linux kernel and GCC, in
particular, are massive projects that have long grown past the scale
of a single person's understanding. But the theory was that a
community of humans can understand collectively.
Now we seem to be throwing up our hands and giving up on
that community. That LLMs will just fix the problem, whatever it
is. But we're all just one rug pull away from being completely
incapable of managing those projects. The argument there is that we'll
just switch to local models, but no one is actually doing that.
All I see is people use local models as a corner case
(for privacy) or as in theory, but in reality, everyone uses the
centralized frontier models right now. We just can't fallback.
We're in the same situation we were, a decade or two ago, when
Microsoft decided it would kill free office alternatives by making
Office free for non-profits. It worked: thousands, if not millions of
schools, community groups and individuals stopped looking for
alternatives (including free software but also "piracy") for Office
and embraced what seemed like a generous offer.
Now Microsoft pulled the plug and Over 170,000 Nonprofits Lost All
Their Data.
I'm afraid the rug pull on LLMs will be much worse: never mind that
Linus won't be able to use his tireless helper to fix obscure kernel
bugs; we're looking at a collapse of the economy so large that we are
already talking about bailing out the companies responsible.
In a sense, the most striking thing about the Debian vote is it has
actually no option to completely refuse upstream LLM contributions. It
seems the community has taken it for granted that it's now impossible
to build Debian entirely without LLMs. We lost the battle even without
a fight, it seems.
A plea for small
If it has really become impossible for us to manage the complexity we
have built, maybe it's time to stop and think about what we're doing
in the first place. We're struggling to even bootstrap our
current toolchain!
This is one of the things I like the most about working on the mesh:
it's low tech, small Arduino devices that is built with decades-old
semiconductor processes that is understandable by human
beings.
Maybe the answer lies more in single-purpose devices like those
communicators and simpler multi-purpose computers than what we have
now, which is what the permacomputing movement is about.
Small is beautiful, let's scale it down.
> llm logs status
Logging is ON for all prompts
Found log database at /home/anarcat/.config/io.datasette.llm/logs.db
Number of threads logged: 7
Number of turns logged: 12
Number of legacy conversations: 543
Number of legacy responses: 970
Database file size: 9.61MB
> llm logs list -n 0 --json jq -r .[].datetime_utc sed 's/-.*//' sort uniq -c
527 2024
357 2025
98 2026
- there is now Claude 5, and a fable model, maybe you know about it?
- impress me
- not impressive, i already know all of this
- chat
- in postfix, i have a 300k mailing that happens regularly here. normally, it delivers within about...
- is there a way i could have drained the maildrop queue faster without removing the milter?
- the problem was that rspamd was timing out on the FUZZY_CALLBACK check. how do i disable that?
- how do i disable all spam checks? i just want rspamd to add dkim signatures
- how do the default_destination_concurrency_limit and initial_destination_concurrency settings int...
- mic check
llm stack I've
been using. The following two are an attempt at seeing what the model
is capable of and I was "not impressed", to which Claude answered that
I have a "high bar", which, fair enough.
The chat is me failing to use a command line, which shows that
perhaps I need to readjust that "high bar", again.
The next five are a rather embarrassing debacle in a large Postfix
mailing that went sideways, and where I couldn't find an actual
Postfix expert of my level to help. The fabled Claude Fable 5 answered
rather correctly, but dangerously, that I could empty the queue by
disabling the non_smtpd_milters. What Fable (and myself) did not
realize is that the milter was also adding DKIM signatures, so while the
mailing was expedited, it was done without those precious signatures,
which got us promptly blocked at Gmail. We have recovered since, and,
thanks to the model and reading the Postfix manual for the
hundredth time, that pickup(8) is single-threaded and that we
needed to review the architecture of that mailing (and our spam
filters) a bit. Many tickets ensued.
The last one is a test I did to make sure my last uploads of
llm-anthropic and its dependency worked correctly.
Note that the above excludes 5 questions I asked Anthropic while writing this article, where I asked for synonyms and "what nanometer scale are arduino processors built from? how is an arduino CPU printed?", a question which Wikipedia furiously evades providing a good answer.Those prompts are pretty typical of my LLM use: I'm testing the models to see if they work at all, but also, out of desperation, I fire off a prompt after I fire off questions to colleagues or search engines (in that order). It's often weird edge cases like the Prometheus query language, Python's matplotlib, LaTeX, Elisp, optimizations, and so on. I use models for translation a lot. Being fully bilingual, it is common for me to think of a word in French or English and fail to find exactly the right word for that in the other language. Models help with that, and are also useful to find synonyms. Those are low-token uses that seem pretty innocuous to me, but I realize the irony of this after writing about the tower of Babel.
What I am not using models for
I am not using models to write prose.
I am not using models to read prose. If it's generated with LLMs, I
stop reading.
I am not using models to write code, with the exception of that single
Python script above.
I am generally not using models to review code, with exceptions. If
I get stuck on a hard problem, I might feed a piece of code to the
model. I repeatedly fed asncounter into Claude to try to fix a
performance regression I had introduced. It found micro-optimizations
that taught me a thing or two about Python's internal implementations,
but overall, it was mostly a waste of time. This was in June 2025, so
perhaps now models would fare better. I have not tried again.
I am not using LLMs to do Debian packaging. When I can, I manually
review the diffs of packages I upload into Debian, still, by hand.
I do this for the reasons outlined in The Four Horsemen of the LLM
Apocalypse, because I refuse to be
complicit in the:
- aggressive and illegal scraping of the servers I steward
- world-wide computer hardware shortage (making it, by the way,
nearly impossible to run presumably clean local models) and the
attack on our job conditions (also discussed in
The people vs the AI overlords)
- death of copyright and free software
- complication and enshifitication of everything, and the
destruction of our communities
- the imperialist Nerd Reich that wants to take over the world
Like I reluctantly use Intel computers, I do fire off a prompt. But
I still hold on to the dream that we can build communities of
practice that hold human knowledge collectively and not offload
that as a utility to some megalomaniac billionaire.
Their LLM use I am forced into
So that's me. Clearly, I'm going against the grain here. Everywhere I
look, I see LLM-generated code and projects. Slop and botnets have
flooded the web.
I use Wadamesh, clearly vibe-coded, because it's the best
graphical interface for MeshCore that runs on portable devices. I wish
it was made by a human, in a community I could participate in, but it
isn't, and I don't.
I package the above llm toolset, which is more and more
vibe-coded, but I still review the diffs. And I have to say: I
trust Simon here. The code is verbose as hell, feels overengineered,
and llm feels slow, but it generally works, and Simon is still at
the gate.
The Anthropic SDK is another thing entirely. The 0.91.0 to 0.120
upload, for example, was nuts:
806 files changed, 72281 insertions(+), 1478 deletions(-)
I explicitly did not review that entire diff. It feels like there's a
lot of garbage there to just have a shim between a proprietary API and
Python. But this is the hand I've been dealt.
Larger projects LLM use
LLMs are being used in the Linux kernel, Firefox, rsync, Rust, and
other places. I don't feel good about this, particularly in Rust, but
they at least made a decent policy. I am glad GCC made a policy
against LLM contributions and I support the human Emacs
project.
We need to have a set of foundational tools that are "clean" in the
sense that they are built upon a community of people that understand
how they are built.
Maybe that's naive or even impossible. The Linux kernel and GCC, in
particular, are massive projects that have long grown past the scale
of a single person's understanding. But the theory was that a
community of humans can understand collectively.
Now we seem to be throwing up our hands and giving up on
that community. That LLMs will just fix the problem, whatever it
is. But we're all just one rug pull away from being completely
incapable of managing those projects. The argument there is that we'll
just switch to local models, but no one is actually doing that.
All I see is people use local models as a corner case
(for privacy) or as in theory, but in reality, everyone uses the
centralized frontier models right now. We just can't fallback.
We're in the same situation we were, a decade or two ago, when
Microsoft decided it would kill free office alternatives by making
Office free for non-profits. It worked: thousands, if not millions of
schools, community groups and individuals stopped looking for
alternatives (including free software but also "piracy") for Office
and embraced what seemed like a generous offer.
Now Microsoft pulled the plug and Over 170,000 Nonprofits Lost All
Their Data.
I'm afraid the rug pull on LLMs will be much worse: never mind that
Linus won't be able to use his tireless helper to fix obscure kernel
bugs; we're looking at a collapse of the economy so large that we are
already talking about bailing out the companies responsible.
In a sense, the most striking thing about the Debian vote is it has
actually no option to completely refuse upstream LLM contributions. It
seems the community has taken it for granted that it's now impossible
to build Debian entirely without LLMs. We lost the battle even without
a fight, it seems.
A plea for small
If it has really become impossible for us to manage the complexity we
have built, maybe it's time to stop and think about what we're doing
in the first place. We're struggling to even bootstrap our
current toolchain!
This is one of the things I like the most about working on the mesh:
it's low tech, small Arduino devices that is built with decades-old
semiconductor processes that is understandable by human
beings.
Maybe the answer lies more in single-purpose devices like those
communicators and simpler multi-purpose computers than what we have
now, which is what the permacomputing movement is about.
Small is beautiful, let's scale it down.
llm toolset, which is more and more
vibe-coded, but I still review the diffs. And I have to say: I
trust Simon here. The code is verbose as hell, feels overengineered,
and llm feels slow, but it generally works, and Simon is still at
the gate.
The Anthropic SDK is another thing entirely. The 0.91.0 to 0.120
upload, for example, was nuts:
806 files changed, 72281 insertions(+), 1478 deletions(-)
It has now been thirty-three years since the Debian project was 
About 95% of my Debian contributions this month were 
While many Western democracies seem to be in a state of decay and are no longer the safe, civilized and prosperous countries they once were, there are still some European countries that are governed well. One of those that stand out is Estonia.
Estonia is probably most well known for multiple software companies that originated from there, such as 
Estonians also seem to value the school system highly. The government has been actively 
This is not just my personal experience. According to the 
The next step is to buy a local prepaid SIM card at e.g., an R-Kiosk or a convenience store as signing up for other matters later on will require an Estonian phone number. Once you have an apartment and e.g., signed a rental agreement, you can register in the population registry online.
After that, you have proof you are a local resident with an address and telephone number in Estonia. With local resident status, you can go to the police station to get a local ID card. Don t bother scheduling an appointment, just go to the 
Welcome to post 57 in the 
The recurring joke is that because of some health issues, in summer I
dress like a Victorian Vampire.
But how would an actual Late Victorian Vampire dress? Picture her, she
would look like some kind of eccentric gentlewoman, as vampires usually
do, probably with a style that is a bit conservative, rather than
following the latest fashions.
Now, she wouldn t probably wear men s shirts. But what if she was a
lesbian
At the front, I wanted the ruffle to be inserted in the yoke, but I was
also whipstitching the gathers to it to make them neater, so I started
bu attaching the yoke lining to the gathered front, then I whipstitched
the ruffle to the front, catching each gather, and finally I
whipstitched the other yoke on the ruffle and the rest of the gathered
front.
And then after sewing the collar, I realized that this way the slit
would have remained open in the front (or the collar too narrow), so I
had to unpick the front part of the yoke, and sew it again, this time
leaving an excess of fabric as wide as half the placket width from the
pattern, to be sewn directly in the collar band.
From then, things progressed smoothly, with some interruptions, until I
got to the first sleeve, which I failed to insert twice, as one does.
On the third attempt, with a different method, I succeeded, I tried the
shirt on, and it already felt extra.
But it could be even more extra. With some ruffles also at the collar.
The shirt had been made with a simple collar band, and I could have just
added the ruffle to it, but I also wanted to be able to wear it with
other detachable collars, so I decided to make another collar band with
ruffles, to wear on top.
And that was mostly it, except for the reinforcement patches at the
side seams and cuffs: I love having them, because they make the seam
end neater and stronger, but they are a bit of a hassle to make, so they
got postponed a few days.
But finally, the shirt was done.
And I tried it on, and it was good.
But now I really need a pair of cycling breeches, don t I?
