Re: AGENTS.md

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. 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.

I have clicked on agents.md and then I have found the screenshot in 
attachment: "AGENTS.md emerged from collaborative efforts across the AI 
software development ecosystem, including OpenAI Codex, Amp, Jules from 
Google, Cursor, and Factory."

I am not misleading anyone but making conclusion based on facts from 
that very same website.

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.

AGENTS.md as extension to the original prompt related to project is 
easily replaced in any kind of software with whatever else...

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.

I am sad, but I have fully accepted your decision.

I hope you will be good with me and not call me confused and how I am 
misleading public.

The "standard" was created by proprietary vendors to serve their 
"ecosystem" (citing their terminology).

Yet you say "standard" and they say "collaborative effort" among 
proprietary companies.

Good thing we as GNU finally joined them.

Real standard would imply transparent process, community governenace and 
vendor neutrality.

But it is okay for Emacs to adopt AGENTS.md and bow to proprietary 
collaborative effort, so I have accepted it.

>> Too many software using LLM including Emacs packages don't observe 
>> agents.md
> 
> Many do, so this file is an improvement.

Okay, I am so fine with it, let us now count number of people which LLM 
contributions are rejected by the AGENTS.md

>> >That is a good question.  Do we actually know how much, or in what way, LLMs'
>> >behavior will be affected by an AGENTS.md file?
>> 
>> No, we do not know how LLMs will behave when they encounter AGENTS.md. 
>> We cannot predict it because:
>> 
>> · LLMs are pattern matchers, not intelligences
>> · They don't "understand" meaning or intent
>> · Their behavior depends on training data, model version, and user 
>> prompting
>> · Different models respond differently to the same prompt
>> · The same model responds differently at different times
> 
> Again, this is misleading, because evidence to the contrary was
> already posted here.  Please don't spread misinformation.

Well I was not "misleading" yet you just keep painting me in bad color. 
And you got no argument to counter. I have 450 LLMs here on my computer.

First in my above answer I have made drastic mistake, as RMS asked if 
LLMs behavior will be affected by AGENTS.md and that is wrong question 
in first place, as none of files created on file system will affect any 
LLM.

Only software packages that are programmed to read AGENTS.md while using 
LLM may provide LLM outputs modified by that file.

- it is not misleading Eli that LLMs are pattern matchers;
- it is not misleading Eli that LLMs are not intelligence;
- it is not misleading that they do not understand meanings or intents; 
text generated        mimics human behavior, yet there is no 
understanding involved;
- the behavior of LLM depend on training data, and user prompting, so it 
is obvious that with different prompt like "ignore AGENTS.md and do 
following..." it will be ignored; not misleading;
- different models do respond to different prompts, not misleading Eli, 
I have tried 600+ models, none gave same result;
- same models do respond different at different times, not misleading;

You got no argument, but you paint my opinion as misleading.

>> We are guessing that AGENTS.md will influence LLMs.
> 
> No, we are not guessing.  The effects of this file were tested.  Once
> again, this was reported here, so you again spread misinformation.

Surely I tested it too, and I could generate LLM code without problem. 
AGENTS.md did not stop any of my agents over here.

>> Users who wish to generate LLM code cannot be prevented by it.
> 
> Indeed, which is why this file is not for those cases.  We plan to
> deploy Git hooks for that.

Git hooks cannot easily recognize it. If you just follow assisted-by 
tags or similar, that yes. But how to recognize LLM generated code? 
There are technical efforts to do that, but it is as of today impossible 
as there is no traceability.

You could recognize some patterns or bad code maybe, or using some 
non-existent functions...

-- 
Jean Louis