Re: AGENTS.md

> Date: Thu, 06 Aug 2026 09:55:28 +0300
> From: Jean Louis <[email protected]>
> Cc: [email protected], [email protected], [email protected],
>  [email protected]
> 
> On 2026-08-06 08:20, Eli Zaretskii wrote:
> >> Date: Wed, 05 Aug 2026 21:40:39 +0300
> >> From: Jean Louis <[email protected]>
> >> Cc: [email protected], [email protected], [email protected],
> >>  [email protected]
> >> 
> >> On 2026-08-05 15:03, Eli Zaretskii wrote:
> >> >> Date: Wed, 05 Aug 2026 12:48:22 +0300
> >> >> From: Jean Louis <[email protected]>
> >> >> CC: [email protected], [email protected], [email protected]
> >> >>
> >> >> On August 5, 2026 8:06:42 AM GMT+03:00, Richard Stallman <[email protected]>
> >> >> wrote:
> >> >>
> >> >> >Eli wrote:
> >> >> >
> >> >> >    Do we have any idea how effective is this in practice?  Does this
> >> >> >    prevent what we want to avoid with likelihood that is close enough to
> >> >> >    100% for us to consider it the "solution"?  Because if not, we'd need
> >> >> >    this _and_ the hooks as Plan B.
> >> >>
> >> >> It's notion (agents.md)to have one file that modifies LLM prompt so
> >> >> that proprietary companies don't need to invent many different files
> >> >> so that their software can run easy and that they minimize their
> >> >> development cost.
> >> >>
> >> >> It's not effective in practice.
> >> >
> >> > This is false, as you have been pointed out already (and said then you
> >> > didn't know it).  Please be fair and mention this when you answer such
> >> > questions, instead of misleading people.  Here's that URL again:
> >> >
> >> >   https://agents.md/
> >> 
> >> You are acting like I have some bad intentions.
> > 
> > Your intentions are none of my business.  What you do and say here is,
> > however.  And what you say above is disingenuous, because you repeat
> > inaccurate or incorrect information, despite the fact that information
> > to the contrary was already posted, and you should stand corrected.
> 
> You have no arguments

The arguments were already posted here many times.

> only attacking me personally.

Not you personally, but what you write here.

> You accusations are unfounded.

They are based on what was already said here many times, with facts
and pointers to Web sites.

> My last argument was related to reasons why AGENTS.md was invented. It 
> was definitely not invented as free as in free software, as otherwise we 
> are all free to add additional prompts to the LLMs in many ways 
> possible.
> 
> It was invented by OpenAI and given to the AGENTIC AI FOUNDATION.

The original reasons for the invention and its authors are not very
relevant, once the results becomes an accepted de-facto standard, and
can help us having prevent LLM-generated code in some cases.

> And then you come again and again telling me how I am misleading people. 
> I am quoting from website.

Your quotes are partial: you ignore the parts that don't fit your
opinions.  So yes, they mislead.

> Yet, you have no argument to say what is exactly misleading?

Everything you ignore, what have already been explained and described
here many times.

> Thus AGENTS.md is simple text that get added to the system prompt.

Yes.

> It is very trivial for any free software to add additional prompt 
> (equivalent to AGENTS.md) to the user's prompt. It is as simple as 
> concatenating strings.

We don't have control on the software our contributors use when they
work on code they later submit as part of their contributions.  So we
cannot in practice cause these prompts to include the instructions we
would like.  This file is one way of doing that that does not rely on
the software our users use when working on code they intend to submit
to us later.

> Thus my logical conclusion is that it is their collaborative effort, the 
> effort that belongs to Google, OpenAI, Anthropic, and few others who 
> started with it -- and for which reason?

Once again, their original reasons are not relevant.  We are using
this file for our purposes, which were already explained many times.

> So you keep telling me I am disingenuous yet you do not provide the 
> argument. What is exactly misleading?

See above.

> What exactly I should "stand corrected"?

Your claim that this file is a proprietary standard supported only by
few proprietary LLM harnesses.

> >> Yes, I did not know it
> >> is any kind of "standard" and it is not a standard. It may become in
> >> future, and surely software packages are adopting it.
> >> 
> >> But telling me how I am "not fair" points out like I am coming to say 
> >> my
> >> above statement in some unjust way.
> > 
> > You are spreading misinformation, which is unfair at least to people
> > like RMS who cannot always cope with the flood of messages here, might
> > not remember the previous posts which contradict what you write, and
> > could thus draw incorrect conclusions based on your misinformation.
> 
> You keep negatively painting my messages.

Yes, because they keep reiterating incorrect and inaccurate
information, although it was already refuted here.

> Yet you do not say what is exactly misinformation? I wonder.

Yes, I did.  Please re-read the thread.

> If I have said anything factually incorrect, please point it out 
> specifically. I will correct it immediately.

People and myself already have.  Please re-read the discussion.

> > Many free/open software standards are initially the result of
> > cooperation by commercial entities.  That doesn't mean the standard is
> > useless or that GNU should ignore it.  We decide whether to support or
> > ignore a free/open standard judging by its usefulness for our
> > purposes, not by irrelevant aspect such as who invented it and why.
> 
> As I said, I am fine with Emacs accepting AGENTS.md and finally I have 
> no saying, but my opinion stays.

You are entitled to your opinions, but please don't increase the
noise level here by repeatedly posting them, when they were already
disproved and rejected.

> >> These are all proprietary companies or proprietary tools:
> >> 
> >> - OpenAI (proprietary)
> >> - Google (proprietary)
> >> - Cursor (proprietary)
> >> - Factory (proprietary)
> >> 
> >> Considering that they do spend much time on development, having 
> >> unified
> >> AGENTS.md only serves the proprietary consortium. Not to free software
> >> or free software community.
> > 
> > If more and more LLM-based agents, including free ones, support this
> > standard, it does serve the free software community.  And regardless
> > of that, the file we added is intended to affect all kinds of LLMs,
> > free and proprietary.  As already explained gazillion times.
> 
> Does AGENTS.md serve free software community? Surely yes. Though primary 
> it serves proprietary vendors who care less for free software community. 

Why "primary"? this file is used by all the LLMs which support it
alike.  Its contents, which we wrote, instructs all of them to do the
same.  There's no preferences here, so the "primary" part is factually
incorrect.

> The file added doesn't affect any LLM automatically.

It affects automatically those LLMs which are programmed to read such
files.

> You wish to say that AGENTS.md affects various software agents who rely 
> on it or want to read it.

An LLM-based agent does not and cannot "want" anything.  It is either
programmed to read the file as part of the prompt, or it isn't.  If it
is, then the instructions there will have their effect.

> Question remains if Emacs policy is against LLM-code generated by 
> software agents, or by the LLM anyhow, without software agent?

I already answered that question: yes, the current policy is not to
accept such code.

> > This all seems like your knee-jerk reaction to seeing the names of
> > proprietary LLM agents, without thinking about the issue at hand and
> > the best ways of dealing with it.  We decided to add this file because
> > it will in at least some cases prevent innocent mistakes on behalf of
> > our contributors.  The file does not mention any specific LLMs, its
> > contents is LLM-neutral plain text.  Thus your objections to it make
> > little or no sense, certainly compared to its positive effect when it
> > is processed.
> 
> You are rude to me. Yet I talk about technical and ethical things in the 
> way I see them function. If you disagree could you tell that somehow in 
> civilized manner?

I see nothing rude in what I wrote.  I disagree with you, to say the
least, and I'm asking you (again) to stop repeating the same opinions
of yours that have been already overturned by evidence.  But that is
not rudeness.

> Now is already few years that I run LLMs on my computer. So technically 
> I cannot see reason how you can prevent users' to generate code using 
> LLM by providing AGENTS.md and I pointed out reasons why.

We never said this measure will always work.  As was already written
here many times.  So your repeated arguments about this are a
strawman.

> >> I have fully accepted Emacs developers decision to include the
> >> proprietary OpenAIs contribution "AGENTS.md" to the so called "Agentic
> >> AI Foundation" and that Emacs follows standards of those proprietary
> >> companies.
> > 
> > This again twists our real purpose and the actions we did by
> > deliberately using denigrating words that have no real relevance to
> > the case.  Simply put, it is a false accusation based on nothing but
> > random words you read without interpreting what they mean.  Once
> > again, evidence to contradict what you say here was posted up-thread,
> > and you keep ignoring it.
> 
> Not denigrating. We are on same page, just disagreeing on details. I do 
> not read "random words" -- please, what did I do to you? I am arguing 
> here technically and ethically.

You are trying to make a point not by technical arguments (which are
all against you), but by using negative epithets.  That doesn't make
your arguments strong at all.

> There is assumption here on mailing list that many people will use 
> "agents" to contribute to Emacs code.

No, there's no such assumption.  It is not for us to assume which
tools people use to program the code they submit to us.

> I am personally surprised, as most comfortable way of generating the
> code in Emacs is by using Emacs buffers.

It was, and still is, a long-standing tradition of the GNU Project
that we don't care which development tools were used for the
contributions.  We don't ask users which editor or compiler they used,
nor whether these tools were free software or proprietary.  All we
care about is that the resulting code is free software.  Likewise in
this case.

But with the possibility of using LLM-based code generators being real
nowadays, we want to take measures we can to prevent such code from
being submitted.

> So yes, adding AGENTS.md is more like a joke, as whoever knows how to 
> guide LLM agents, they will simply ignore or remove the file.

No, it isn't a joke.  It is a serious measure with real results that
uphold our current policy at least in some cases.

> No real enforcement of a policy.

It wasn't supposed to be an enforcement.  It was supposed to be a
useful tool to prevent inadvertent mistakes.