News for hackers. Stuff that matters.
Re:Getting 50% (SoTA) on Arc-AGI with GPT-4o by awwaiid on Monday June 17, 2024 @09:23PM (#40713140)
I think it's more like humans are a chaotic choir of subsystems all doing their thing and tossing up their directives until some sort of "win" happens or the volume is loud enough in some direction that it then gets reverse engineered into a "thought". But yes.
Re:Getting 50% (SoTA) on Arc-AGI with GPT-4o by badrunaway on Tuesday June 18, 2024 @07:39AM (#40716559)
like darwin selection between the subsystem approaches? Put in a lot of different kind of LLMs and let them play the same game inside with each other.. whosoever wins the simulation is allowed to externally present the approach... something like that?