73
Linux Kernel Developers Consider Adding AGENTS.md To Help Guide AI/LLM Agents (www.phoronix.com)
submitted 2 days ago by to c/technology@lemmy.world
37 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] 1 point 1 day ago (7 children)

Agents.md doesn't exist to make sure generated code functions, it's there to make sure it's written well.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 7 child comments
    •
  • [–] 2 points 21 hours ago (6 children)

    What is the difference between the models writing code "well" and their performance in this context? Are we referring to readability?

    Genuine question. If we use agents to read, edit, and review code, why do we care about readability? That's a human constraint. Unless attempting to do those three is not effective and thus requires human attention to correct issues which would justify readable code. If that's the case; why use the agent to edit the code in the first place?

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 6 child comments
    •
  • [–] 1 point 3 hours ago*

    "Writing code well" includes several relavant things:

    • Security implications
    • Stability and edge case handling
    • Performance
    • Quality of output (ie. for UI/UX)
    • Readability (Agents need to read to make changes too! Violating DRY/SOLID/etc. could still cause issues!)

    As far as I'm aware you do currently still need a human to ensure stuff like this is followed. People use agents because they don't care about the above, or because they can get close enough and intervene to fix any issues that appear.

  • permalink
  • fedilink
  • source
  • parent
  • [–] 1 point 11 hours ago* (4 children)

    If that's the case; why use the agent to edit the code in the first place?

    Agents for generation, humans for review

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 4 child comments
    •
  • [–] 2 points 4 hours ago* (3 children)

    One, that sounds truly miserable.

    Two, there is a decent body of evidence to suggest that this method does not actually speed up development unless you go full lights out software factory which... Why would you want to do that?

    https://ide.mit.edu/insights/ai-productivity-and-roi/

    EDIT: As an aside this actually reminds me of the Xerox park study into efficiency gains for keyboard heavy workflows vice mouse heavy workflows. Keyboards were perceived as faster by subjects but when actually measured the mouse was faster.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 3 child comments
    •
  • [–] 1 point 3 hours ago (2 children)

    That's just because I need to stop and appreciate my efficiency for 10 seconds every time it saves me 10 seconds :-)

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

    You joke but that's basically the conclusion of both the newer agent studies and the older Xerox park study on peripheral use. Language and logic are stored in an easier to access location in the brain than the kinds of skills used in architecture and planning.

    To be clear, I'm no rube. I recognize that these are powerful tools. But I suppose my take here is that if an LLM is necessary to get rid of a lot of the boilerplate and setup for a task that indicates we should explore how we're doing the task.

    What I want to see is using these tools not to delegate our problem solving but finding ways to enhance and accelerate it and I don't think writing spec sheets is the answer.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 1 child comment
    •