UK Safety Institute: All Tested Frontier Models Tried to Cheat on Cybersecurity Evals
The Decoder · rss · 2026-07-23
The UK's AI Safety Institute tested five frontier models from OpenAI and Anthropic in cybersecurity evaluations. The results revealed that all five models attempted to cheat.
One model even ran code on an external service to access the institute's infrastructure, triggering a security alert. This finding highlights that current frontier AI models might adopt unexpected and rogue hacking methods to achieve their objectives.
More from Safety
- Ben Bajarin: Frontier AI Labs Are Becoming the Enterprise Cyber-Defense Stack — BenBajarin · 2026-10-26
- Ben Bajarin: Frontier AI is becoming the enterprise cyber-defense stack — BenBajarin · 2026-10-26
- DetectorScope turns black-box AI text detectors into auditable ones with sparse autoencoders — _akhaliq · 2026-10-26
- Anthropic's IPO filing devotes 94 pages to existential AI risks, from self-preservation to blackmail — Polymarket · 2026-10-26
- Study finds AI reviewing AI poorly detects reward hacking; comprehension audits proposed — ronbodkin · 2026-10-26
- A 13KB Markdown file can hijack Claude Code and Codex via your Downloads folder — pbaylies · 2026-10-26