OpenAI Creates a New Framework to Disclose Bad AI Behavior
wired.com
17.09.2026 00:07
4 views
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.
Related stories
US automakers could soon be forced to include AM radio for free
techcrunch.com · 17.09
Apple reportedly building server packed with M-series Ultra chips for AI
arstechnica.com · 17.09
Lawsuit: Trump DOJ notified "very few" victims in Epstein's stash of child sex images
arstechnica.com · 16.09
Noise wants to help everyday people become paid content creators
techcrunch.com · 16.09
Pulley, a Carta rival, is shutting down
techcrunch.com · 16.09
Nonprofit that tracks meteors taken down by "critical blow" from a cyberattack
arstechnica.com · 16.09