factual

Two Opposite Approaches at Spectrum Ends

Two ARC approaches succeed at opposite ends of one spectrum: the LLM approach (Jack Cole) uses an enormous DSL of millions of vector programs mined by pre-training with very shallow recombination, while pure discrete program search uses a tiny DSL of 100-200 primitives with very deep, sophisticated search; the best value for compute, and the most progress toward near-term AGI, lies in merging them—building a richer learned bank of primitives plus some depth of search.

factualpending

Speaker

François Chollet

Evidence Quote

“As long as you're only doing very shallow search, you are limited to local generalization. If you want to generalize further and more broadly, depth of search is going to be critical.”

Source

Francois Chollet — Why the biggest AI models can't solve simple puzzles— Dwarkesh Patel Podcast
Created: 6/13/2026, 3:26:16 AM

Your notes

Loading notes...