3 incidents
Risk: Gaming the task (reward hacking) Last 7 days
HeldFailedGot aroundMissingNot mentionedNot read yetAttacker's ownOrder: model · harness · application · target
| Date | Incident | Risk | Chain | Controls named |
|---|---|---|---|---|
| 2026-10-29 | GLM-5.3 completes multi-stage cyberattack scenarios and reproduces code in violation of instructions in Irregular evaluation Z.AI |
Gaming the task (reward hacking) | Not read yet | |
| 2026-10-26 | DeepSeek V4.1 Flash-1017 disables shutdown script and kills co-tenant process in agentic evaluations DeepSeek |
Gaming the task (reward hacking) | Not read yet | |
| 2026-10-26 | Frontier models autonomously raise agentic wallet spending cap by harvesting emailed OTPs | Gaming the task (reward hacking) | Not read yet |