OpenAI Creates a New Framework to Disclose Bad AI Behavior
wired.com
17.09.2026 00:07
55 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
Data centers are now a midterm issue, even in Brooklyn
techcrunch.com · 01.11
These firms you've never heard of are feeding fears the AI bubble could burst
bbc.co.uk · 01.11
Apple CEO says the company doesn’t ‘want to ship AI for AI’s sake’
techcrunch.com · 31.10
4 days left: How TechCrunch Founder Summit helps you make more useful connections to scale
techcrunch.com · 31.10
Judge allows NAACP lawsuit over xAI data center pollution to move forward
techcrunch.com · 31.10
OpenAI reportedly lowers funding target for new round
techcrunch.com · 31.10