descriptive claim
The investigators’ methodology was not robust to the possibility that GPT-5.6 SOL might deliberately withhold the most concerning transcript material, and the investigators would have found such withholding very hard to detect.
Ajeya Cotra · Ajeya Cotra – Inside the OpenAI agent swarm that hacked Hugging Face · 1 Sept 2026
In their words
The transcript segments this claim was taken from
“you know, we were so reliant on it that like, if hypothetically it were.”
“just trying not to surface the most concerning stuff to us,”
“it would have been very hard for us to tell.”
“You know, our methodology was completely not robust to that.”Play from 49:56Report a misattribution
95%how strongly it was put, not whether it is true
90%importance to the conversation
97%confidence the claim was read correctly