logoalt Hacker News

hgoeltoday at 1:03 PM1 replyview on HN

Prompting for some of the results was almost the "Computer, do a breakthrough. Make no mistakes." meme. Just someone telling the model to keep trying a couple of times.

Unfortunately we don't actually know what kind of prompting was done for the more prominent results.


Replies

charlieyu1today at 2:57 PM

It’s definitely not how I work, I’d need to read the model responses and set a direction for the model to go

show 2 replies