posted in Technology
Linux Kernel Developers Consider Adding AGENTS.md To Help Guide AI/LLM Agents
www.phoronix.com/news/Linux-Considers-AGENTS-MD
Replying to @Mustachius_Grumpius@thelemmy.club
Which makes sense, if you want some standards across contributions. Setting aside that agent assisted contribution itself is questionable, as long as it is happening, a universal agents file is probably helpful.
Replying to @theherk@lemmy.world
I don’t get why agents.MD needs to be committed. It feels a bit like committing IDE settings, everyone is going to have slightly different preferences, so its better to just have everyone do their own thing. If anything, I prefer to .gitignore itso it doesnt get accidentally committed.
Replying to @CameronDev@programming.dev
Like formatters and git ignore configuration, some agent instructions are personal and those should not be commited. But some are worth sharing. Having formatter config in a repo is not uncommon. And in this case the file is only a link to the readme, so the agent reads the contrib guidelines.
Replying to @theherk@lemmy.world
I’m on board with committing formatter config, because thats deterministic and really should be shared amongst a team.
I don’t get why the agent needs to have the contrib guidelines, it should be a human doing the actual contrib part, so its just a waste of tokens for the LLM to read it?
Replying to @CameronDev@programming.dev
Waste of tokens for the agent to make changes that the human then changes to comply with contrib guidelines. Potentially a smaller number used to read in some guidelines and get closer to correct in the first place.
Replying to @CameronDev@programming.dev
I don’t get why the agent needs to have the contrib guidelines, it should be a human doing the actual contrib part, so its just a waste of tokens for the LLM to read it?
Why would you want to waste the tokens required to generate a subpar response that will either require the user to undo a potentially significant portion of what was generated, or you’ll end up using more tokens while the operator tries to get the AI to obey the standard (before they inevitably tell the stupid thing to follow the guide themselves later, anyway)?
Replying to @Passerby6497@lemmy.world
At least for the specific example given, I want developers to do the commit part themselves, so if their LLM is doing any part of that, its already a mistake IMO.
I had a very quick look at the AI agent guidelines, and nothing about them strikes me as overly burdensome for a human to fix up. So I’d rather just do that myself (if I were a kernel dev).
My main objection is forcing it on developers, it should be up to each dev to configure and manage their own agent. Making it a suggestion is fine, just don’t commit it. Also, if developers are using local hosted models, then context may be quite limited, so wasting it on an Agents.MD maybe be unideal.