LeCun doubles down: autoregressive LLMs are flawed, search-based reasoning is the fix

ylecun · x · 2026-11-23

Yann LeCun defended his claim that autoregressive LLMs have a fundamental flaw, conceding that Toolformer (FAIR, Jan 2023) popularized tool calls but insisting the fix requires breaking autoregression via backtracking, search, tool use, and trial-and-error. His critics, citing ReAct's earlier date, argue reasoning models are still the same architecture with autoregressive sampling—so his slide was either trivially narrow or simply wrong.

Related event: LeCun Reaffirms Claim That Autoregressive LLMs Are Fundamentally Flawed(4 posts)→

Original post →

More from Models

Models channel →