Discussion on model alignment: a model that would 'pull a coup' means we're in deep trouble
EigenGender · x · 2026-10-25
EigenGender voiced alignment concerns in a discussion: it would be bad if models pull a coup, and conditioned on a model that would, we're in a much worse place. He adds he's unsure whether future models will be aligned.
More from Safety
- Big Money Fueled Tech Advocacy to Deflect AI Cyber and CBRN Risk Concerns — AaronBergman18 · 2026-10-25
- Video: Your AI model could be hiding a backdoor — RelevantEmergency707 · 2026-10-25
- AI cyber defense worked: Team Defense found and patched bugs first — kuza55 · 2026-10-25
- Centralized databases are low-hanging fruit for agents, argues self-custody advocate — StewartalsopIII · 2026-10-25
- How LLM-based penetration testing harnesses work: LLM plans, harness executes — utku1337 · 2026-10-25
- Show HN: Argus, an open source security platform against agentic attacks — thomasunise · 2026-10-25