AgentHarm to Expand AI Misuse Benchmarks
maksym_andr · x · 2026-07-09
This post cites details about AgentHarm: the task suite was originally designed to measure whether models pursue harmful goals, making it an ideal proxy when early models were less capable. As models approach real-world deployment, subsequent evaluations will incorporate more complex agentic misuse benchmarks.
More from Research
- Structural ensembles beat single predictions in TCR:pMHC generalization study — quaidmorris · 2026-07-22
- Structural ensembles, not single predictions, drive robust TCR:pMHC generalization — quaidmorris · 2026-07-22
- enFoldX turns AlphaFold3 ensemble noise into a TCR–peptide–MHC predictor — quaidmorris · 2026-07-22
- enFoldX tops 8 neoantigen scans and an unseen-peptide benchmark — quaidmorris · 2026-07-22
- enFoldX reaches AUC 0.82 on human VDJdb and transfers to mouse at 0.76 — quaidmorris · 2026-07-22
- enFoldX extracts 106 interface and confidence features from AF3 ensembles — quaidmorris · 2026-07-22