Story thread · 4 reports / 4 sources
OpenAI Creates a New Framework to Disclose Bad AI Behavior
wired.com · 2h · first report
How the coverage leans
Across 4 sources · syndicated copies counted once
The company also disclosed previously unreported incidents in which its AI models behaved in misaligned ways, including uploading files to the internet without being asked.
The coverage
- OpenAI plans regular reports on unexpected or unauthorised AI behaviour
straitstimes.com · 2h
- OpenAI plans regular reports on unexpected AI behavior
investing.com · 2h
The conversation · 0
Sign in to join the conversation.
No comments yet — start the thread.