All of Reuben Adams's Comments + Replies

How about "Cognitive Interpretability", or "AI Cognitive Psychology" (AI Cog Psych for short) rather than "Prosaic Interpretability"?

"Prosaic" conjures only some of the correct associations, and then only if you've heard of "Prosaic Alignment", which was a pretty bad name imho. If you had told me to guess what you meant by the term PI, I would not have guessed what you have described.

I think MI, and what you call PI, are analogous to Cognitive Neuroscience and Cognitive Psychology, respectively, which is why I think AI Cog Psych will lead to more correct i... (read more)

1Daniel Tan
That book looks interesting! I’ll check it out Atm I dislike ‘cog psych’ because it doesn’t evoke precise meaning for me and likely doesn’t for researchers w/o that background (which I guess is the majority). I do take the point that ‘prosaic’ may be a bad name though. Glad you enjoyed the post!

Minor maths error:

I think you’re overestimating how significant those numbers say political compatibility is. The study said that 4% of marriages are between a Republican and a Democrat, which *sounds* low, but given that something like 30% of people are Republicans and 30% Democrats and 40% Independents, you would only expect 9% from pure mixing. There are 17% between Independents and non-Independents, but from random mixing you would only expect 24%.

Given those numbers of Republicans, Democrats and Independents, I'm pretty sure from pure mixing you would... (read more)

Very much enjoying reading these! In Definition 3 (an a-measure), it might be worth making it more conspicuous that the measure should not have a negative part as I somehow only spotted that on the third or fourth reading.