AI brief
The post links to a paper on predicting how propensities generalize out-of-distribution, which began as a SPAR project. The authors selected 24 propensities, elicited each through 4 methods, and tested how this spills over to non-targeted traits.
Written by AI from LessWrong's published text.
Source
“This is a link-post for our new paper " Predicting how propensities generalize out-of-distribution ", which started as a SPAR project.”
Interpretation or community commentary rather than straight reporting.
Read original story ↗