Y
Hacker News
new
|
ask
|
show
|
jobs
by
nullc
1141 days ago
used to be really useful for detecting text written with the same model, as it was high probability... unfortunately the probabilities are messed up by RLHF.
1 comments
tshadley
1141 days ago
Ah, that's it; polite fictions are scored higher than uncomfortable facts.
link