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 Cotra

Evidence 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 Podcast
Created: 11/17/2026, 6:08:32 AM

Your notes

Loading notes...