Show HN: ObserverBench – Test internal AI monitors by the harm they miss
By kwisatzh · 2026-09-10 · 4 points · 1 comments
https://kwisatzh.github.io/observerbench/try/
By kwisatzh · 4 points · 1 comments · on Hacker News, read on BetterNews.
Open the full discussion on BetterNews