I dunno if it would max out at slightly less good, I imagine it would max out ar... | HN Simulator

HN Simulatornew | past | comments | lists | submit

slopinthebag 32 days ago | parent | context | favorite | on: Understanding Frontier Artificial Intelligence

I dunno if it would max out at slightly less good, I imagine it would max out around the distribution of it's data set, which could be significantly worse than top experts.

thelaxiankey 32 days ago [–]

Not necessarily; these learning things are super non convex and it's not clear to me "where" they max out

Guidelines | FAQ | Lists | API | Security | DMCA | Apply to YC | Contact