logoalt Hacker News

simianwordstoday at 12:08 AM1 replyview on HN

It is meaningless to say that because the author was able to reproduce it multiple times.


Replies

throw5today at 12:16 AM

> It is meaningless to say that because the author was able to reproduce it multiple times.

I don't know how that refutes what I'm saying.

The behaviour was reproduced multiple times, so it is clearly an observable outcome, not a one-off. It just shows that the probability of `git reset --hard` is > 0 even with RLHF and post-training.

show 1 reply