Archive
Sequences
About
Search
Log In
Questions
Events
Shortform
Alignment Forum
AF Comments
Home
Featured
All
Tags
Recent
Comments
Measure comments on
Language models seem to be much better than humans at next-token prediction
Measure
12 Aug 2022 14:24 UTC
3
points
0
I was doing okay until I blew my lead guessing that the model wouldn’t predict a typo.
Back to top
I was doing okay until I blew my lead guessing that the model wouldn’t predict a typo.