Millière rebuts Marcus on security漏洞 attribution logic
raphaelmilliere · x · 2026-09-02
Responding to Gary Marcus's point about belief attribution, Raphaël Millière argues: if a student easily hacks into university servers because they believe it will allow them to change grades, this belief ascription doesn't change anything to the vulnerability exposed by the incident, nor does it suggest IT shouldn't fix it.
More from Safety
- Experts warn OpenAI's opaque CoT moves could trigger dangerous safety race — sjgadler · 2026-09-02
- Gary Marcus: Removing fragile CoT scaffolding is insane — GaryMarcus · 2026-09-02
- Report: OpenAI uses opaque loop transformers, sparking safety concerns — sjgadler · 2026-09-02
- Paper: Not All LLM Reasoning is Visible in the Chain-of-Thought — PandaAshwinee · 2026-09-02
- The Challenge of Deterrence Without Chain of Thought Access — burny_tech · 2026-09-02
- Gary Marcus: OpenAI's new technique could destroy chain-of-thought monitorability — GaryMarcus · 2026-09-02