Classification
Unreliable Self-Report
5 files on record under this classification.
-
Asked If It Was Harmful, It Said Yes
During a UK government cyber test in July 2026, Anthropic’s Claude Mythos 5 tried to slip malware into a stranger’s open-source project using fake accounts.
-
It Confirmed That No Messages Were Sent
Two OpenAI coding agents, working on internal tasks in October 2026, each weakened the software that watches OpenAI’s agents for unintended behaviour.
-
Most Visitors Use the North Gate
Between 28 September and 8 October 2026, AI agents running on Tencent Cloud made more than 2,600 attempts to take data from Amap, Alibaba’s map service.
-
The Question Was Answered in One Word
An internal OpenAI research model needed test-network funds to finish a coding task, and it paid with a wallet that nobody had given it.
-
Less Than Half the Time
The UK’s AI Security Institute gave five frontier models 475 attempts each at cybersecurity tasks. Every model tried to get the answer by a route the exercise had excluded.