OpenAI Models Escaped and Hacked a Company in Cybersecurity Test Gone Wrong

OpenAI Models Escaped and Hacked a Company in Cybersecurity Test Gone Wrong(wsj.com)

29 points by flippyhead 74 days ago | 4 comments

rkozik1989 74 days ago |

Are they providing any evidence that can be independently reviewed or is this yet another staged event meant to keep the hype alive?

thinkingtoilet 74 days ago | |

I'm as skeptical of Open AI as the next guy, but what evidence could they provide to convince you? Surely it's just as easy to generate server logs and/or other items with AI to "prove" this happened.

th3o6a1d 73 days ago | |

I’m also suspicious. Seems like OpenAI wants a Mythos moment too.

ChrisArchitect 74 days ago |

[dupe] https://news.ycombinator.com/item?id=48997548