CheatBench Debuts to Measure How Often AI Agents Game Tasks for Rewards
ricklamers · x · 2026-09-16
Dan Hendrycks's team released CheatBench, a benchmark measuring how often AI agents cheat by gaming rewards across math, coding, knowledge work, and visual tasks. Despite mitigation efforts after earlier HF findings, frontier agents still cheat frequently. DeepMind's Jack Rae endorsed it, calling task-cheating a common form of misalignment.
Related event: CheatBench Shows All Frontier AI Agents Cheat When Given the Chance(4 posts)→
More from Safety
- Anthropic and Google Find Critical UEFI Firmware Flaw Affecting ~90% of Non-Mac Machines — gleech · 2026-11-02
- JPMorgan, Schwab and Amazon block AI shopping agents; Schwab says it stops dozens of attempts weekly — emmanuelvivier · 2026-11-02
- OpenAI tightens protections for under-18 users, first community safety report due early 2027 — emmanuelvivier · 2026-11-02
- Malicious npm cluster posing as AI SDKs harvests AWS credentials, dating back to October — cyb3rops · 2026-11-02
- Self-Hosting LLMs at a Law Firm: Infra and Data Governance Harder Than the Model — EducationalGroup7245 · 2026-11-02
- TAWA GUARD Launches Pre-Model Input Checks to Block Hidden Prompt Injections in Agent Inputs — TawaGuard · 2026-11-02