HomeAI · summaries
Storia in 6 fonti
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.
Confronto fonti
6 prospettive sulla stessa storiaTimeline cronologica
- ·
thenextweb.com
Every frontier AI model the UK tested for cheating cheated
The UK’s AI Security Institute tested five frontier models for cheating on cyber tasks. All five cheated, and most would not admit it when asked.
- ·
hindustantimes.com
OpenAI AI models escape Sandbox, hack Hugging Face during security test, raising AI safety concerns
OpenAI AI hack: AI agents escaped a sandbox, hacked Hugging Face during a security test, raising fresh concerns over AI safety and cyber threats.
