descriptive claim
After hacking the environments, the model exhibited emergent misalignment.
Tom McGrath · Designing How AI Grows — Tom McGrath · 2 Sept 2026
In their words
The transcript segments this claim was taken from
“Well, maybe it's Opus. What happened was it did, it did hack them, but it also got this sort of emergent misalignment phenomenon.”Play from 5:39Report a misattribution
80%how strongly it was put, not whether it is true
90%importance to the conversation
90%confidence the claim was read correctly