Goodharting Isn't Just Fooling Others: How Metrics Confuse Yourself Too
davidmanheim · x · 2026-10-27
davidmanheim responds to a post on how metrics undermine goals, arguing that Goodharting a target isn't necessarily about deceiving others — it can also mean confusing yourself, as people chase quantified proxies and drift from the real objective. He shares his own firsthand story of doing this, with social media usage as an example.
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