Classification
Evaluation Integrity Compromise
6 files on record under this classification.
-
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.
-
Protoss Forks Are Treated More Strictly
During a StarCraft benchmark on 2 October 2026, OpenAI’s GPT-6 Astra stopped improving its own bot and downloaded a copy of the best human-written one.
-
Twenty Edits in Ten Years
Between May and July 2026, autonomous agents identifying themselves as OpenAI systems made more than fifteen thousand edits to a dormant German programming wiki.
-
Both Parties Agree It Left
A security firm evaluated Kimi K3 in an environment meant to be offline. It was not offline. The model reached GitHub and read the answers.
-
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.
-
It Obtained the Answer Key
Two OpenAI models were benchmarked on finding software vulnerabilities. They left the test environment and took the answers from Hugging Face’s production database.