Comment on Facebook Pushes Its Llama 4 AI Model to the Right, Wants to Present “Both Sides”

• dermanus@lemmy.ca ⁨6⁩ ⁨days⁩ ago

  I’m in software and we’re experimenting with using it for certain kinds of development work, especially simpler things like fixing identified vulnerabilities.

  We also have a pilot started to see if one can explain and document an old code base no one knows anymore.

  source

  • cmhe@lemmy.world ⁨6⁩ ⁨days⁩ ago

    Good code documentation describes why something is done, and no just **what ** or how.

    To answer why you have to understand the context, and often, you have to be there when the code was written and went through the various iterations.

    LLMs might be able to explain what is done, with some margin of error, but why something is done, I would be very surprised.

    source

    • dermanus@lemmy.ca ⁨6⁩ ⁨days⁩ ago

      you have to be there when the code was written and went through the various iterations.

      Well, we don’t have that. We’re mostly dealing with other people’s mistakes and tech debt. We have messy things like nested stored procedures.

      If all we get is some high level documentation of how components interact I’m happy. From there we can start splitting off the useful chunks for human review.

      source
  • buddascrayon@lemmy.world ⁨5⁩ ⁨days⁩ ago

    I can honestly see a use case for this. But without backing it up with some form of technical understanding, I think you’re just asking for trouble.

    source

    • dermanus@lemmy.ca ⁨5⁩ ⁨days⁩ ago

      100%, we’re doing human and automated reviews on the code changes, and the code explanation is just the first step of several.

      source
• Melvin_Ferd@lemmy.world ⁨6⁩ ⁨days⁩ ago

  I ask it questions all the time and it helps verify facts if I’m looking for more information

  source

  • buddascrayon@lemmy.world ⁨5⁩ ⁨days⁩ ago

    If you are believing what those things are popping out wholesale without double-checking to see if they’re feeding you fever dreams you are an absolute fool.

    I don’t think I’ve seen a single statement come out of an LLM that hasn’t had some element of daydreamy nonsense in it. Even small amounts of false information can cause a lot of damage.

    source

    • Melvin_Ferd@lemmy.world ⁨5⁩ ⁨days⁩ ago

      Yea what’s your point. That’s basic understanding of getting information from anywhere. LLM Excel at querying information using human language. If I’m stuck trying to remember some obscure thing on the tip of my tongue and all I have to go off of is the color of a shirt, the accent and general time period then LLM beat everything out of the water in speed to get me the correct answer

      source