✳flâneur — a map of the web's best reading

Musings on the Speed Prior — AI Alignment Forum

alignmentforum.org · 4,389 words · saved by 1 readers

Thanks to Paul Christiano, Mark Xu, Abram Demski, Kate Woolverton, and Beth Barnes for some discussions which informed this post. In the ELK report, Paul, Mark, and Ajeya express optimism about penalizing computation time as a potentially viable way to select the direct translator over the human imitator: Human imitation requires doing inference in the entire human Bayes net to answer even a single question. Intuitively, that seems like much more work than using the direct translator to simply “look up” the answer. [...] Compared to all our previous counterexamples, this one offers much more hope. We can’t rule out the possibility of a clever dataset where the direct translator has a large enough computational advantage to be preferred, and we leave it as an avenue for further research. I am more skeptical—primarily because I am more skeptical of the speed prior's ability to do reasonable things in general. That being said, the speed prior definitely has a lot of nice things going for

x Musings on the Speed Prior — AI Alignment Forum Eliciting Latent Knowledge AI Frontpage 23 Musings on the Speed Prior by evhub 2nd Mar 2022 12 min read 4 23 Thanks to Paul Christiano, Mark Xu, Abram Demski, Kate Woolverton, and Beth Barnes for some discussions which informed this post. In the ELK report , Paul, Mark, and Ajeya express optimism about penalizing computation time as a potentially viable way to select the direct translator over the human imitator: Human imitation requires doing inference in the entire human Bayes net to answer even a single question. Intuitively, that seems like

Explore this link on the map →

related reading