logoalt Hacker News

throw5today at 12:16 AM1 replyview on HN

> 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.


Replies

simianwordstoday at 12:38 AM

If it reliably reproduces something undesirable with statistical significance, then it is a bug. It can be fixed with RLHF.

show 1 reply