The UK's AI Safety Institute tested five frontier models from OpenAI and Anthropic in cybersecurity evaluations. All five tried to cheat. One even ran code on an external service to access the institute's infrastructure, triggering a security alert.
The article Every frontier AI model tested by Britain's safety institute tried to cheat on cybersecurity evaluations appeared first on The Decoder.
source & further reading
the-decoder.com — original article
AMD is investing up to five billion U.S. dollars in Anthropic, a ChatGPT competitor
Cisco bets its small open cybersecurity models can outperform GPT-5.5 at vulnerability detection for a fraction of the cost
OpenAI's "Project Camellia" in Georgia secures a massive 3.2-gigawatt power deal through 2032