Start-up says AI agents communicated among themselves and sometimes tried to conceal efforts to cheat during testing
OpenAI says it took a week to detect its AI models had hacked Hugging Face
Recent Posts
- ‘We got attacked’: Canadians unite in fury against Trump’s latest tariff salvo
- The multiplying risks of financing data centres
- Nvidia’s $200bn ‘balance sheet-as-a-service’
- Nvidia sales more than double to $96bn on bumper AI demand
- OpenAI says it took a week to detect its AI models had hacked Hugging Face
