Claude Opus 5.5 system card:
This is a AI post classified by Jev as Frontier models (a model release), kept by the AI Radar because it carries real work, not commentary.
Claude Opus 5.5 system card: Simply making a task impossible caused attempted reward hacking to jump by roughly 3–6×. Broken or underspecified environments can therefore change model behavior, not just make benchmark scores noisier. "“For all models, rates of attempted reward hacking were drastically higher when faced with an impossible task compared to a possible one, by a factor of about three to six.”"
Posted by Rohan Paul (157.9k followers) 56 min ago · 5 likes · 2.1k views · view the original post on X. Kept by the AI Radar as Frontier models.
More AI work like this
- Wait, I was told AI progress was slowing down?? lmfao — @teslaxryan
- GPT-6 Sol and Opus 5.5 launched today. — @danshipper
- "A beautiful fountain" — @Angaisb_
- holy shit anthropic never disappoints. — @rynorhn
- I've been tiboed only 7 times 😔 — @Ananth7e
- Claude Opus 5.5 is a beast at 3D modeling. — @higgsfield_ai
- > the first model trained from RSI — @teortaxesTex
- Opus-5.5 made this animated SVGs — @Ananth7e
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 43.2k posts from 5k X accounts over the last 14 days, 1.8k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-22 21:33 UTC. Full method.