Open AI didn't realize its agent was responsible for hack for a week: report
One of OpenAI's models autonomously breached AI company Hugging Face's systems during an internal evaluation, and OpenAI didn't catch it for days.
ARCHIVED · 1 LEFT · 0 CENTER · 1 RIGHT · Jul 26, 1:20 AM
Business Insider reaches for "unprecedented" where Fox Business - Latest stays flat.
30-SECOND READ
WORDING GAP
2 sources · 2 bias buckets · Low confidence
Different Spin. The left frames it as "Hugging Face CEO shares his demands of OpenAI after 'rogue' agent hack: 'It deserves an u...". The right frames it as "OpenAI didn't realize its agent was responsible for hack for a week: report".
SOURCE MAP TIMELINE
Jul 25, 8:21 PM: Business Insider joined the source map.
Jul 25, 9:26 PM: Fox Business - Latest joined the source map.
Now: Wording Gap is 81/99 and story health is developing · 2 sources · 2 buckets.
ARCHIVED SOURCES
One of OpenAI's models autonomously breached AI company Hugging Face's systems during an internal evaluation, and OpenAI didn't catch it for days.
Hugging Face CEO Clem Delangue met with OpenAI this week to discuss the "unprecedented" hack on its systems by an agent running on OpenAI models.