News for hackers. Stuff that matters.
Re:Getting 50% (SoTA) on Arc-AGI with GPT-4o by HarHarVeryFunny on Monday June 17, 2024 @07:08PM (#40712233)
Actually the solution being discussed here is the one that Chollet mentioned in his interview with Dwarkesh, and only bolsters his case.

The LLM isn't doing the reasoning here, it's just pattern matching the before/after diff and generating thousands of Python programs. The actual reasoning is done by an agentic like loop wrapped around the LLM, as described in the linked blog.

Re:Getting 50% (SoTA) on Arc-AGI with GPT-4o by awwaiid on Monday June 17, 2024 @09:26PM (#40713162)
When you peer into the soul of the machine it delicately resolves to `while(1){...}`. All Hail The REPL.