François Fleuret: AR models can do FOL perfectly without any FOL in their definition
francoisfleuret · x · 2026-09-26
Pushing back on the claim that next-token prediction fundamentally caps LLMs, François Fleuret argues a model's formal definition lacking a property doesn't mean the process it implements lacks it too. Example: train an autoregressive model on vast first-order logic examples and it will do FOL perfectly, with no FOL in its formal definition.
More from AGI Musings
- tqbf leaves Fly.io as Simon Willison calls tech's year '100 years at once' — mhmazur · 2026-09-26
- mitsuhiko: Austria adopted cars 30 years late — temper your AI rollout expectations — mitsuhiko · 2026-09-26
- Bostrom's anti-anthropomorphism advice isn't the same as saying LLMs can't think — maksym_andr · 2026-09-26
- Anthropic's earliest investor Jaan Tallinn dances hip-hop while warning of tech that could end humanity — KateClarkTweets · 2026-09-26
- Adoption lags frontier: why OpenAI staff AI use may mirror average users — maksym_andr · 2026-09-26
- Swarm hype critique: a loop is not AGI — frozen models just sampled more — gerardsans · 2026-09-26