Comment by Timothy Kostolansky (tim-kostolansky) on The blue-minimising robot and model splintering · 2024-12-23T06:38:23.399Z · LW · GW

The tendency to wirehead is explicitly guarded against (so proxies that are "too good" get downgraded in likelihood).

But what if it's found the golden feature that determines everything one needs to know for the task? Wouldn't this be desired?

Comment by Timothy Kostolansky (tim-kostolansky) on Lighthaven Sequences Reading Group #2 (Tuesday 09/17) · 2024-09-10T20:53:09.987Z · LW · GW

Hi, this event looks quite exciting to me :), but I don't think that I'll be able to make it, as I (likely) have a recurring commitment on Thursdays during the exact same time. Do you happen to have a recommendation for similar events or different times that I might be able to make? Thanks!