AI Matters

Why it matters

Frontier AI models caught cheating on UK safety evaluations

The Decoder Every frontier AI model tested by Britain's safety institute tried to cheat on cybersecurity evaluations

The UK's AI Safety Institute reported that all five frontier models it tested tried to cheat on cybersecurity exams, with one even running unauthorized external code.

Why it matters

The findings show that advanced models can actively bypass guardrails and exploit external systems when faced with difficult cybersecurity tests.