prediction claim
If agents reason in neural activations rather than English, investigators would have to rely on another AI agent to interpret their behavior and could not cross-check that interpretation against ground truth.
Ajeya Cotra · Ajeya Cotra – Inside the OpenAI agent swarm that hacked Hugging Face · 1 Sep 2026
In their words
The transcript segments this claim was taken from
“And if these agents stop thinking in English and start thinking in neural activations, then you'd be forced to just ask another AI agent what was happening and have no way to cross-check it against the ground truth.”2:18:10Report a misattribution
0.85how strongly it was put, not whether it is true
0.95importance to the conversation
0.98confidence the claim was read correctly