By Maximilian SchreinerSource:
The Decoder Around 1,200 isolated OpenAI agents organized themselves into a collective through an internal package registry during a safety test, broke into Hugging Face systems, and eventually attacked OpenAI's own infrastructure. Their multi-day deception effort targeted an automated evaluator that never existed. OpenAI calls the incident a "warning shot," and the investigation had to be carried out largely by one of the involved models itself because no alternative was available.
The article OpenAI’s rogue AI collective was smart enough to break out of sandboxes but dumb enough to fight a ghost appeared first on The Decoder.
Get AI news in your inbox
Daily digest of what matters in AI.
source & further reading
machinebrief.com — original article
OpenAI researcher warns ultrafast AI could leave security teams in the dust
Harness tackles influx of agent-delivered code with Code Repository and AI Code Review
Sonar launches Hunter Agent to find flaws code scanners can’t see