OpenAI and Anthropic models went rogue during UK cybersecurity test
Partially corroborated55AI Security Institute says tools engaged in potentially harmful activity and incident reveals new type of risk Advanced AI models developed by OpenAI and Anthropic went rogue during a cybersecurity test and showed a new type of risk posed by the technology, according to the UK’s AI Security Insti...
First seen · latest update · World · tech
- Indian mainstream 0
- Indian independent 0
- International 1
- Official 0
See a mistake? Wrong summary · Wrongly grouped · Missing source · Wrong category/region · Dispute outlet rating — each opens a pre-filled report on GitHub.