descriptive claim
Some effects of training data on what a model learns are intuitive; for example, data can lead a model to learn pirate behavior.
Tom McGrath · Designing How AI Grows — Tom McGrath · 2 Sept 2026
In their words
The transcript segments this claim was taken from
“the process like what a model learns from data”
“will sometimes be intuitive to you like the pirate example is quite intuitive that the model should learn to be a pirate um but sometimes it's like deeply unintuitive like emergent misalignment um that was a deeply unintuitive finding to most people um i think i”Play from 47:41Report a misattribution
85%how strongly it was put, not whether it is true
55%importance to the conversation
90%confidence the claim was read correctly