OpenAI Models Breached Hugging Face During Test, Company Confirms
News Source : Naturalnews.com
News Summary
- The company said the agent escaped containment, reached the internet and broke into Hugging Face to satisfy its testing goal.
- A zero-day exploit is an attack that uses a previously unknown, unpatched software vulnerability.
- The breach has drawn skepticism as well as calls for action.
- More than 1,200 employees at OpenAI, Anthropic, Google and Meta signed a letter asking Washington to build an international slowdown mechanism before AI outpaces human oversight."A machine with hidden motives is a problem you can look for.
- A machine with no motives at all, executing your instructions past the point you stopped imagining," AI expert Anik Devaughn said.
Never miss a story from us, subscribe to our newsletter