180
Linus Torvalds posts his first AI-assisted patch to the Linux kernel, synthetic test clocks 23x performance leap — the bossman makes use of AI tooling himself after issuing clear pro-AI directives (www.tomshardware.com)
submitted 1 day ago by to c/technology@lemmy.world
129 comments fedilink hide all child comments
 

cross-posted from: https://piefed.social/c/linux@programming.dev/p/2509642/linus-torvalds-posts-his-first-ai-assisted-patch-to-the-linux-kernel-synthetic-test-clo

you are viewing a single comment's thread
view the rest of the comments
[–] 32 points 1 day ago (18 children)

Human review of AI is sufficient in theory, but in practice it's never as thorough as the understanding you get writing it yourself. It's hard to avoid AI, but it is a constant invitation to laziness.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 18 child comments
    •
  • [–] 19 points 1 day ago (16 children)

    Unlike reviewing a human who writes code there is zero chance of AI learning from the past and making fewer mistakes in the future. At a least a human has a chance of becoming better at coding from review feedback.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 16 child comments
    •
  • [+] -16 points 1 day ago (14 children)

    No? Are you not aware of the concept of "memories"? AI do indeed take feedback into account, if they're designed to.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 14 child comments
    •
  • [–] 17 points 1 day ago (11 children)

    AI does not have memories.

    It has a comparatively small context window that makes things worse the more it fills up.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 11 child comments
    •
  • [+] -12 points 1 day ago (8 children)

    You are mistaken. Some AI models do indeed have memories.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 8 child comments
    •
  • [–] 9 points 1 day ago (7 children)

    They save some strings in a document to later read and "remember". Calling them memories is a reach.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 7 child comments
    •
  • [–] -5 points 1 day ago (6 children)

    My point stands that they can learn from feedback. Your memories are only information in a virtual document, too. Just as susceptible to corruption, or misinterpretation.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 6 child comments
    •
  • [–] 4 points 18 hours ago (3 children)

    Does an Alzheimer's patient learn things just because they read the same note every morning explaining the reality to them?

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 3 child comments
    •
  • [–] 0 points 11 hours ago (2 children)

    No, their file system is corrupt. No reliable read or write access.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] 1 point 11 hours ago (1 child)

    The AI is no different from the girl in "50 First Dates (2004)". It has to go back and read the post-it notes every time you start a new session. It does not retain memory without writing shit down to read later.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 1 child comment
    •
  • [–] 9 points 1 day ago (1 child)

    The auto-generated memories I've seen it create are pretty inane: "always name variables container_ when in MySpecificClass". Not really learning engineering principles.

    Similar, I've found AGENT.md files might nudge it in the right direction, but as always it's a fuzzy matcher, not a learning engineer.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 1 child comment
    •
  • [+] -7 points 1 day ago

    It's best to generate memories manually, but I've had good fortune with auto-generated so far. At least using Co-pilot.

    I have found it best to have another AI generate the agent.md - having a layer of interpretation can really clarify the information imparted.

  • permalink
  • fedilink
  • source
  • parent