François Fleuret Proposes Tagging Every Token 'Heard/Thought/Said' to Solve Alignment
francoisfleuret · x · 2026-10-28
Former Meta/Apple research scientist François Fleuret outlines his personal take on solving alignment:
- Pre-training should include a substantial RL component — let the model talk from the beginning.
- Every single token should be tagged "heard," "thought," or "said."
- A "mother model" encourages or chides only the "said" tokens, never the "thought" ones.
The core idea: separate inner monologue from outward speech, constraining only what the model expresses so it can think freely while speaking responsibly.
Related event: Ex-Meta Researcher Fleuret Proposes Token-Tagging Approach to AI Alignment(3 posts)→
More from AGI Musings
- Stack Overflow posts fewer than 1,000 questions in a month, down 99% from peak — DanielLockyer · 2026-10-28
- AI progress feels normal now — P vs NP is the next real benchmark — haider1 · 2026-10-28
- Amodeis' Neurotech Remarks Spark Debate Over Human-AI Coevolution at Anthropic — burny_tech · 2026-10-28
- What happens to advertising when AI agents do most online shopping? — VraserX · 2026-10-28
- Rumors: OpenAI and Anthropic internal models gain reasoning via RL in games and simulated environments — imjustnewatai · 2026-10-28
- Jeremy Avigad: the AI debate belongs at the center with us, not the AI — Machine Learning Street Talk · 2026-10-28