descriptive claim
Tom McGrath says jailbreaks are probably the clearest example of a language model behaving coherently while appearing to have gone haywire from its creators' perspective.
Tom McGrath · Designing How AI Grows — Tom McGrath · 2 Sep 2026
In their words
The transcript segments this claim was taken from
“make them go haywire although i would say that jailbreaks are an example probably the best example of what you're talking about you know there it has like it's doing something coherent but from the perspective of its its creators it has gone haywire”1:11:43Report a misattribution
0.75how strongly it was put, not whether it is true
0.75importance to the conversation
0.90confidence the claim was read correctly