Re: AGENTS.md

On 2026-08-06 07:42, Eli Zaretskii wrote:

>> Did you test all the millions of LLMs on it?
> 
> Is this a serious question?

You said you tested LLM. Yet there are millions of LLMs. So I am 
pointing out that it is better you express yourself specifically.

You probably tested just the software agent. LLM is normally not trained 
on AGENTS.md so it is not relevant testing the "LLM".

And yet in that testing, why not say in transparent what exactly did you 
test?

- which software?
- which LLM was tested?

Software package that recognizes AGENTS.md would guide LLM to recognize 
it. Yet without any guarantee. Testing something like that (multiple 
LLMs) is not easy process. You would need to have GPU running and know 
how to load models.

If you have tested remote LLMs with some software agent most probably 
you tested those proprietaries. Yet those are just few among millions. I 
have tested many LLMs running on my computer and they will not behave 
same. You can get files deleted. Database can get deleted. There is no 
guarantee with LLMs neither. I have gone through all that, so now I 
learned how to behave so that those dangerous activities never get 
invoked.

>> Or we are just creating AGENTS.md for commercial software using LLM?!
> 
> Again, we created it to help users making innocent mistakes, using
> whatever LLM-based agents, both proprietary and free.  The Emacs
> policy is not to accept code generated by LLM-based agents regardless
> of whether they are free or not.  As was repeatedly explained here.

AGENTS.md is not to help users. It is by specification to guide software 
agents, not users.

Users are guided by README or CONTRIBUTE.

AGENTS.md is not for the LLM, but for the buffer, harness or software 
agent which specifically recognizes such. Thus large number of LLM 
software that can modify files and generate code is left uncontrolled.

I was all the time thinking that Emacs policy is not to accept LLM 
generated code.

Now you said it is the policy not to accept LLM-based agent generated 
code.

Please, clarify it, is it fine then to generate code by LLM if we do not 
use LLM-based agents?

-- 
Jean Louis