Re: Dealing with LLMs in IETF discussions draft

Stephen, Chong Feng,

Pretty good starting point for a discussion.

Coming back on "you are responsible for what you post" (Laurence 
Lundblade), I completely agree. The IETF is a meritocracy.
In this meritocracy, I have to admit to pay more attention to some 
individual opinions. Why, because, historically, their opinions is worth 
reading. If someone sends BS/LLM generated emails or drafts, this person 
will go in my ranking with the side effect that I will pay less attention.

I know the draft is called "Dealing with LLMs in IETF Discussions" and 
my next remark might be off context
When posting a draft, I encourage the use of LLMs as a tool to resolve 
spelling mistakes, idnits,  IANA considerations alignement with the 
registration procedure, technical mistakes, inconsistencies, etc. I know 
of one Designated Expert already using this type of tools.
I believe that posting a draft these dasy without going through a AI 
tool is a waste of time for the entire IETF community.
On top of that, the months spent in the RFC editor queue these days 
could be shortened thanks to those IETF specific tools.
Note: a recall a time when the IESG was flagging spelling mistakes in 
reviews. :-(

Note: I added a spelling mistake above, on purpose, to demonstrate my 
identity :-)

Regards, Benoit

On 31/07/2026 03:20, Stephen Farrell wrote:
>
> Hi all,
>
> Myself and Chong Feng have posted an I-D [1] that (from two
> pretty different perspectives) aims to progress discussion
> of how we might better handle LLM text in IETF discussions.
>
> I think this'd be a fine topic for broad discussion. I do
> not know what would be the correct mailing list for such a
> discussion, but also think it doesn't warrant waiting for
> another round of dispatchery before being discussed. (Nor
> would any dispatch outcome above 'new mailing list' suit.)
>
> So, I'd be v. interested in comments on this and/or on it
> being moved to some other mailing list for discussion. If
> no existing list suits, I'd suggest [email protected]
> (which could be contracted to [email protected]:-) as a name
> for a new list, but whatever works is fine.
>
> Meanwhile, we'd be v. interested in any comments here or
> on the github repo [2].
>
> And of course, this is a v. rough thing, not intended to
> be prescriptive or authoritative, so have at it:-)
>
> Cheers,
> S.
>
> [1] https://datatracker.ietf.org/doc/draft-fengfar-led/
> [2] https://github.com/sftcd/led/
>