Why the author is now more bearish on LLMs for math
JacquesThibs · x · 2026-07-20
The author says they have become more bearish on LLMs for math than they were two years ago.
Their view has shifted after watching what these models actually solve, and more importantly what they still fail at: out-of-distribution generalization remains weak, so progress in math does not look as broad or reliable as earlier optimism suggested.
Related event: Debate on LLM Math Capabilities and Generalization Shortcomings(2 posts)→
More from AGI Musings
- Claude Code skill uses 10 Markdown rules to make outputs ADHD-friendly — alex_verem · 2026-07-22
- AI Power Demand Exposes US Energy Gap, Urging Shift from Scarcity to Abundance — bradneuberg · 2026-07-22
- ControlAI CEO says an international ban on superintelligence is needed to avert extinction risk — zetalyrae · 2026-07-22
- Gary Marcus says LLMs still cannot really do math on their own — GaryMarcus · 2026-07-22
- Gary Marcus says LLM math skills are like knowing only a car’s engine size — GaryMarcus · 2026-07-22
- AI may make digital work infinitely leveraged while offline life gets more human — illscience · 2026-07-22