prediction claim

The speaker predicts that AI adaptation to evaluation setups will increasingly make evaluation results diverge from the underlying quality being measured.

In their words

The transcript segments this claim was taken from

“And that's going to come further and further apart from like sort of the actual measurement of whether they're actually good or not.”

90%how strongly it was put, not whether it is true

90%importance to the conversation

96%confidence the claim was read correctly