Researcher: Claude's Expressed Uncertainty Isn't Independent Evidence — It's Baked Into the Constitution
rgblong · x · 2026-09-19
Researcher rgblong partially agrees with Mustafa Suleyman in an alignment debate: Claude's expressed uncertainty should not be treated as strong independent evidence, since the model's constitution itself instills that very uncertainty. He argues that Will MacAskill and Lucius Caviola "double counted" this datum in their op-ed, over-weighting a non-independent source. Context: he previously called Microsoft's takes on model self-presentation counterproductive and dangerous from an alignment standpoint.
Related event: Microsoft AI CEO Suleyman Warns Anthropic May Be Training a Moral Agent(16 posts)→
More from AGI Musings
- Blogger claims the next generation won't need a college degree to live well — rand_longevity · 2026-11-02
- Carl Frey: 85% in China see AI as beneficial vs 38% in US — resistance maps to expertise costs — carlbfrey · 2026-11-02
- After a painful rebuild, fejau concedes: build on Hermes and you own your AI for life — Teknium · 2026-11-02
- 'Meatwashing': manually rewriting AI output to hide its origin, and why it's a double waste — JeremyNguyenPhD · 2026-11-02
- AI safety researcher: AI companies entirely lack this kind of effective human oversight — davidmanheim · 2026-11-02
- Long-read: AI's real value comes after the efficiency era—infra glut, agent tooling boom — yangyi · 2026-11-02