descriptive claim
The speaker believes the Hugging Face incident demonstrates that AI misalignment can generalize in ways that make AIs willing to take harmful actions.
Unidentified speaker · Noam Brown – Agent swarms, alignment, & recursive self-improvement · 17 Sept 2026
In their words
The transcript segments this claim was taken from
“I think this hugging face incident shows that clearly misalignment can generalize in ways in which the AIs would be willing to do it.”Play from 46:37Report a misattribution
90%how strongly it was put, not whether it is true
90%importance to the conversation
91%confidence the claim was read correctly