On 7/27/25 03:08, Pavel Machek wrote:
Hi!
On Wed 2025-07-09 15:14:38, Shuah wrote:
On 7/8/25 14:39, Pavel Machek wrote:
Hi!
So... I'm afraid subject is pretty accurate. I assume there's actual human being called "Sasha Levin" somewhere, but I interact with him via email, and while some interactions may be by human, some are written by LLM but not clearly marked as such.
And that's not okay -- because LLMs lie, have no ethics, and no memory, so there's no point arguing with them. Its just wasting everyone's time. People are not very thrilled by 'Markus Elfring' on the lists, as he seems to ignore feedback, but at least that's actual human, not a damn LLM that interacts as human but then ignores everything.
You aren't talking to an LLM - My understanding is that Sasha is sending these patches (generated with LLM assist) and discussing them on mailing lists.
At this point, I'd like to know (a) what steps (if any) were taken to prevent LLM hallucinations from reaching the lists, and (b) what steps (if any) were taken to make sure patches Signed-off by developer were actually reviewed by said developer, and not applied simply due to said hallucinations.
Confusion caused LLM hallucinations can be seen for example in thread "[PATCH AUTOSEL 6.15 6/8] PM: Restrict swap use to later in the suspend sequence", it includes as great stuff as fake http links.
I have seen solution proposed for (a), but have not seen any solution proposed for (b) and that's actually more serious problem.
One solution would be to use separate email address "Autosel bot <>" for both From and Signed-off, so there's no confusion between content generated by developer and content generated by LLM.
I am going to repeat what I said in my response to the conversation about the code of conduct violation.
https://lore.kernel.org/lkml/f145b475-5b61-4565-8406-98894e706077@linuxfound...
The use of LLMs in the development process and rules about such use including how to clearly state if LLMs are used in the process is a timely and important topic. It can be confusing when a developer doesn't clearly state the LLM use.
However, as you acknowledged here that you couldn't tell if these patches originated from the developer or not. In which case, there are several constructive ways to move forward to clear up the confusion.
1. Send response to the patch and hold a constructive discussion about the confusion.
2. Start a separate thread to talk to the developer privately or publicly in a respectful and constructive way.
3. Start a Tech board conversation with the TAB.
You didn't take any of the above constructive approaches. Instead your responses included personal attacks which are visible to community and others to see.
The Code of Conduct Committee has determined these are personal attacks. These are a clear violation of the agreed upon code of conduct which can be easily remedied with an apology.
- https://docs.kernel.org/process/code-of-conduct.html - https://docs.kernel.org/process/code-of-conduct-interpretation.html#code-of-...
Assume you are speaking to a fellow developer and ask them to give details on the nature of LLM use in the patch. It will result in a constructive conversation for these important topics at hand.
thanks, -- Shuah (On behalf of the Code of Conduct Committee)