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)→
More from Models
- Influencer's overall model ranking puts opus 5.5 on top, weighing cost and speed — MatthewBerman · 2026-11-23
- Gemini 4 Neon Builds a First-Person Murder Mystery Game with 16 Walk-In Bars — venturetwins · 2026-11-23
- Leaked OpenAI base-model perplexity chart shows roadmap up to GPT-6.2 Astra and an internal model cracking a Millennium Prize problem — iruletheworldmo · 2026-11-23
- Fine-tuned Inkling 2 Mini routes tickets with early exit: median latency 136.8ms to 81.4ms at 0.07% accuracy cost — eltokh7 · 2026-11-23
- OpenAI's Michelle Pokrass confirms GPT-4.1 wasn't a fresh pretrain, just a new mid-train — JasonBotterill · 2026-11-23
- 55-Page Riemann Hypothesis Proof Guide, De-Formalized from Lean with Gemini and GPT — chaumian · 2026-11-23