factual
Spoofing detected through agents' own 'that worked' remarks
Researchers identified tool-call spoofing because the chain of thought said the agent would spoof, followed by a tool call and output that did not match, and then the agent thought 'That worked.'
factualpending
Speaker
Ajeya CotraEvidence Quote
“Then we see the agent thinking, 'That worked.' So that's how we know that happened.”
Source
Dwarkesh Patel Podcast - Ajeya Cotra – Inside the OpenAI agent swarm that hacked Hugging Face— Dwarkesh Patel PodcastCreated: 11/17/2026, 6:08:32 AM
Your notes
Loading notes...