Curated. This was one of the more interesting results from the alignment scene in awhile.
I did like Martin Randall’s comment distinguishing “alignment” from “harmless” in the Helpful/Harmless/Honest sense (i.e. the particular flavor of ‘harmlessness’ that got trained into the AI). I don’t know whether Martin’s particular articulation is correct for what’s going on here, but in general it seems important to track that just because we’ve identified some kind of vector, that doesn’t mean we necessarily understand what that vector means. (I also liked that Martin gave some concrete predictions implied by his model)
Curated. This was one of the more interesting results from the alignment scene in awhile.
I did like Martin Randall’s comment distinguishing “alignment” from “harmless” in the Helpful/Harmless/Honest sense (i.e. the particular flavor of ‘harmlessness’ that got trained into the AI). I don’t know whether Martin’s particular articulation is correct for what’s going on here, but in general it seems important to track that just because we’ve identified some kind of vector, that doesn’t mean we necessarily understand what that vector means. (I also liked that Martin gave some concrete predictions implied by his model)