Likely yes, but secretly what motivated my post was a discussion of outlier detection for the purpose of alignment, and for that purpose we can’t just assume a coarsening, as it instead has to be learned or hard-coded.
Current theme: default
Less Wrong (text)
Less Wrong (link)
Likely yes, but secretly what motivated my post was a discussion of outlier detection for the purpose of alignment, and for that purpose we can’t just assume a coarsening, as it instead has to be learned or hard-coded.