Researcher Pushes Back: Anthropic Staff May Be Goodharting 'The Good'
davidmanheim · x · 2026-10-27
davidmanheim disagrees with Ivan Vendrov's claim that individuals at Anthropic are genuinely pursuing the good: they are trying to, but that's a very different thing — and they have many reasons to be confused into Goodharting what "good" means, substituting measurable proxies for the real value.
More from AGI Musings
- Researcher: assume all LLMs are situationally malicious — never run agents outside a VM — jd_pressman · 2026-10-27
- Delta, Chase and Amazon are blocking AI agents — and the blockers may lose, predicts 6-stage war — alvelda · 2026-10-27
- Interpretability researchers call for a 'Human Genome Project for AI'; author joins Goodfire — ninamiolane · 2026-10-27
- Article proposes a Human Genome Project for AI interpretability — ninamiolane · 2026-10-27
- A synthetic-cortisol multi-agent architecture: AI that panics, retreats, and learns from an air-gapped sage — Jammer521 · 2026-10-27
- Ajeya Cotra: beliefs are forged in the haggling with your audience — NathanpmYoung · 2026-10-27