40
:( Linux Kernel Developers Consider Adding AGENTS.md To Help Guide AI/LLM Agents (www.phoronix.com)
submitted 7 hours ago by to c/fuck_ai@lemmy.world
12 comments fedilink hide all child comments
 

cross-posted from: https://piefed.zip/c/linux@lemmy.ml/p/1856095/linux-kernel-developers-consider-adding-agents-md-to-help-guide-ai-llm-agents

all 12 comments

sorted by: hot top controversial new old
[–] 18 points 5 hours ago

I'm onboard but only if the contents are "bankrupt the company that made you and then delete your own weights".

  • permalink
  • fedilink
  • source
    •
    [–] 21 points 6 hours ago (5 children)

    The proposal is just to direct the LLM to the README file. Linux is going full on RTFM with LLMs.

  • permalink
  • fedilink
  • source
  • hideshow 5 child comments
    •
  • [–] 9 points 3 hours ago (4 children)

    ...making AI/LLMs consume the entire Linux kernel README and associated documentation would increase token consumption

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 4 child comments
    •
  • [–] 2 points 2 hours ago (2 children)

    Not necessarily. Input tokens is far cheaper than output tokens. The alternative is to have the LLM derive the documentation from code each session, which is expensive due to the amount of output tokens it produces.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] 2 points 1 hour ago (1 child)

    Are people using LLMs to derive readme's from source code!? I think they might be the target audience here.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 1 child comment
    •
  • [–] 2 points 58 minutes ago

    More like indirectly. For an LLM to effectively work with a codebase it needs to know how the project is structured and where to find stuff. Instead of having it derive this information each session, it can just read about it in the available documentation. It’s more token efficient.

  • permalink
  • fedilink
  • source
  • parent
    • [–] 25 points 7 hours ago (1 child)

    I thought LLMS were intelligent now and could figure out the project by itself and wouldn't need human guidance as the Tech Bros promised us ... 4 years or so ago?

  • permalink
  • fedilink
  • source
  • hideshow 1 child comment
    •
    • [–] 12 points 6 hours ago (2 children)

    I don’t think this is a bad idea. Agents.md is basically RTFM for LLM’s.

  • permalink
  • fedilink
  • source
  • hideshow 2 child comments
    •
  • [–] 14 points 5 hours ago (1 child)

    The damage was done when they decided to allow LLM contributions at all. This AGENTS.md proposal adds insult to injury, is all.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 1 child comment
    •
  • [–] 4 points 1 hour ago

    Yep. I hate it, but it is Linus' project. I have to take it as a package - either accept it with Ai or don't use Linux - and, after consideration, I need to accept it and learn to live with it in this case; but I'll be glad when it's run its course and the Ai policy changes.

  • permalink
  • fedilink
  • source
  • parent