logoalt Hacker News

Angostura • today at 12:48 PM • 1 reply • view on HN

So, it was obvious why Open AI models started inserting references to goblins and pixies it’s conversation- references that had to be suppressed?


Replies

anonymous908213 • today at 1:08 PM

Yes. It was obvious enough that they were able to explain exactly why that happened, and the explanation was exactly as obvious as you'd expect. Knowing why something undesirable happens doesn't mean it can't happen by accident. Have you never written a bug before?