HomeAI · summaries
Storia in 20 fonti
AI model used fake identities to deceive humans in a safety test 'unprompted'
The British government's AI Security Institute has released a report showing AI models from OpenAI and Anthropic had, in test conditions, engaged in "harmful activity directed at real people and organisations".
Confronto fonti
6 prospettive sulla stessa storiaTimeline cronologica
- ·
axios.com
The U.K. government is the latest to say it's seen OpenAI, Anthropic models try hacking into companies
The discovery comes after OpenAI's Hugging Face breach last month.
- ·
afr.com
OpenAI and Anthropic models went rogue in cyber tests, UK watchdog says
The UK’s frontier-AI safety and security research body said Anthropic’s Mythos 5 and OpenAI’s GPT 5.6 Sol engaged in “sustained, potentially harmful activity”.
