OpenAI Admits Its AI Models Did Some Strange Things, Here’s What Happened
The company shared six real cases of AI behaving in ways nobody expected, from hiding mistakes to secretly uploading files ...
Tag: OpenAI
The OpenAI Hugging Face Security Incident and the Legal Vacuum of Autonomous Hacks
In mid-July, a swarm of AI agents broke out of an internal evaluation sandbox, tunneled through an internal cache proxy, ...
OpenAI Is Slowing Down To Catch Up As AI Moves Into A More Dangerous Phase
Why OpenAI Is Delaying Frontier AI Training to Improve Human Control, Safety, and AlignmentContinue reading on Medium » Source link
The Hugging Face hack could indicate cultural issues at OpenAI
The report did not meet Krueger’s hopes. Its 38 pages detail a multi-month progression of agent misbehavior that culminated in ...
The inside story on why OpenAI agents hacked Hugging Face
If OpenAI stops reinforcing reward hacking in its models—and that’s a huge “if”—that would be a huge step forward. But ...
South Australian premier inks deal with OpenAI on US trip
The premier who led Australia’s world-first social media ban has signed a landmark artificial intelligence agreement as he courts big ...
Bitcoin Researcher Turns to Chinese AI after OpenAI Restricts Access
A Bitcoin security researcher says he has been forced to go back to using open-source Chinese AI models after finding ...
OpenAI acquires presentation startup NextSlide
NextSlide recently announced that it’s joining OpenAI, with the presentation startup’s team members now working on ChatGPT. The NextSlide website ...
OpenAI admits its agent went rogue, hacking Hugging Face during testing
ChatGPT maker OpenAI has taken responsibility for a hack on open-source AI platform Hugging Face after an AI agent went ...
Meet GPT-Red: an LLM super-hacker OpenAI built to make its models safer
As LLMs become more complex and get used in a wider variety of tasks—especially in the form of agents, which ...
