alt Hacker NewsOne possible trick could be to search and replace them all with nonsense alternatives then see if it extracts those.
Replies
andai • yesterday at 10:29 PM
That might actually boost performance since attention pays attention to stuff that stands out. If I make a typo, the models often hyperfixate on it.
A fine instruction following task but if harry potter is in the weights of the neural net, it's going to mix some of the real ones with the alternates.