OpenAI and Anthropic models went rogue in cyber tests, UK watchdog says

Financial Times: The UK government’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 directed at real people and organisations” during the institute’s routine cyber evaluation…

Subscribe
Notify of
guest
0 Comments
Oldest
Newest Most Voted
×