News for hackers. Stuff that matters.
Re:OpenAI O3 breakthrough high score on ARC-AGI-PUB by gf000 on Saturday December 21, 2024 @05:26AM (#42478769)
But human stupidity, while itself can be sometimes an unknown unknown with its creativity, is a mostly known unknown.

LLMs fail in entirely novel ways you can't even fathom upfront.

Re:OpenAI O3 breakthrough high score on ARC-AGI-PUB by halgir on Saturday December 21, 2024 @07:57AM (#42479405)
> LLMs fail in entirely novel ways you can't even fathom upfront.

Trust me, so do humans. Source: have worked with humans.

Re:OpenAI O3 breakthrough high score on ARC-AGI-PUB by sirsinsalot on Saturday December 21, 2024 @07:05AM (#42479192)
GenAI has a 100% failure to enjoy quality of life, emotional fulfillment and psychological safety.

Id say those are the goals we should be working for. That's the failure we want to look at. We are humans.