4 sources healthy · latest episode 9 Nov 2026
descriptive claim

The finding of emergent misalignment was deeply unintuitive to most people.

Tom McGrath · Designing How AI Grows — Tom McGrath · 2 Sep 2026

In their words

The transcript segments this claim was taken from

“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”
47:46Report a misattribution
0.90how strongly it was put, not whether it is true
0.75importance to the conversation
0.95confidence the claim was read correctly
The finding of emergent misalignment was deeply unintuitive to most people. · Savlar