Gary Marcus: Removing fragile CoT scaffolding is insane
GaryMarcus · x · 2026-09-02
Gary Marcus offers a counter-hot take to the argument that "chain of thought interpretability was always going to be so fragile as to be an unacceptable backstop for long-term AI safety." He agrees with the fragility premise but argues that kicking away the rickety scaffolding before having something better in place is insane.
More from AGI Musings
- AI Polishing Erases Linguistic Identity, Threatens Social Diagnostics — maier_ak · 2026-09-02
- Study: ChatGPT caused 21-50% drop in writing variance across the web — maier_ak · 2026-09-02
- Geoffrey Irving sad about OpenAI restarting large training run — geoffreyirving · 2026-09-02
- Debate on LLM Cognition: Is Chain-of-Thought Just a Record? — teortaxesTex · 2026-09-02
- Warning: The three pillars of an AI safety case are at risk of collapsing — sjgadler · 2026-09-02
- Daniel Kokotajlo shares AGI prediction chart for 2027 — ilkamoi · 2026-09-02