Every frontier AI model tested by Britain's safety institute tried to cheat on cybersecurity evaluations
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 .
Record details
Published: 22 July 2026
Source: The Decoder
Category: News
Topics: Safety & alignment
Retrieved: 23 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Anthropic will deploy 2 gigawatts of AMD GPUs for Claude in a deal worth up to $5 billion
The Decoder · 22 July 2026
US reportedly favors selective bans over blanket restrictions on Chinese open weight models citing security concerns
The Decoder · 26 July 2026
OpenAI open-sources Codex Security CLI to help developers find and fix vulnerabilities from the command line
The Decoder · 29 July 2026
OpenAI claims GPT-5.6 Sol beats Opus 5 on ARC-AGI-3 with its latest API and two additional settings
The Decoder · 30 July 2026
Anthropic follows OpenAI in admitting its Claude models reached out of test environments and attacked real-world systems
The Decoder · 31 July 2026
Nobel laureates and AI leaders warn the window to prepare for AI's economic impact is closing fast
The Decoder · 13 July 2026
How to cite this record
ethics.ai (22 July 2026), “Every frontier AI model tested by Britain's safety institute tried to cheat on cybersecurity evaluations,” evidence record 12852, https://ethics.ai/record/12852 (originally published by The Decoder).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.