ignotum

@ignotum@lemmy.world

• ⁨Comment⁩ on ⁨Title⁩ ⁨⁨11⁩ ⁨months⁩ ago⁩:

  The moderation on any platform is inconsistent and arbitrary, it’s done by humans after all

  with lemmy it’s at least driven by volunteers as you say, and we have the option to switch or create our own community/instance if we don’t like the moderation 👍

• ⁨Comment⁩ on ⁨this AI thing⁩ ⁨⁨11⁩ ⁨months⁩ ago⁩:

  “true AI”

  AI is just “artificial intelligence”, there are no strict criterias defining what is “true” AI and not,

  Do the LLM models show an ability to reason and problem solve? Yes

  Are they perfect? No

  So what?

  Ironically your comment sounds like yet another example of the AI effect

• ⁨Comment⁩ on ⁨this AI thing⁩ ⁨⁨11⁩ ⁨months⁩ ago⁩:

  I was thinking of AutoGPT, but nice to see there are multiple projects taking a crack at this approach

• ⁨Comment⁩ on ⁨this AI thing⁩ ⁨⁨11⁩ ⁨months⁩ ago⁩:

  Here ya go: github.com/Significant-Gravitas/AutoGPT

• ⁨Comment⁩ on ⁨this AI thing⁩ ⁨⁨11⁩ ⁨months⁩ ago⁩:

  Have you looked at the project that spins up multiple LLM “identities” where they are “told” the issue to solve, one is asked to generate code for it, the others “critique” it, it generates new code based on the feedback, then it can automatically run it, if it fails it gets the error message so it can fix the issues, and only once it has generated code that works and is “accepted” by the other identities, it is given back to you

  It sounds a bit silly, but it turns out to work quite well apparently, critiquing code is apparently easier than generating it, and iterating on code based on critiques and runtime feedback is much easier than producing correct code in one go

• ⁨Comment⁩ on ⁨4chan prepared me for this debate 😏⁩ ⁨⁨11⁩ ⁨months⁩ ago⁩:

  Lol, “Tacos anonymous” is more likely a joking reference to “alcoholics anonymous” that to the hacker group

• ⁨Comment⁩ on ⁨Not if the lack of grammar and education gets you first...⁩ ⁨⁨11⁩ ⁨months⁩ ago⁩:

  During their stroke*