Hacker News new | ask | show | jobs
by SubiculumCode 19 days ago
I do have to say, and this is from recent observations, not outdated ones, but their AI summaries get things wrong, alot, and these are things that gemini (proper), Claude, or ChatGPT subscription AI's don't get wrong.
1 comments
sunaookami 19 days ago
I don't know why their AI summary model is so bad, yet when you just click through to AI mode it's miles better...
link
SubiculumCode 19 days ago
I've noticed that too. I am sure its because the AI summary runs on almost every query.
link
FergusArgyll 19 days ago
It also has to be very fast = small
link