logoalt Hacker News

edotyesterday at 8:39 PM2 repliesview on HN

14 seconds per token? Not tokens per second. Seconds per token? That’s nowhere near the cusp!


Replies

dotancohenyesterday at 11:18 PM

It's need it to be an order of magnitude cheaper, but for some queries ("What to discuss at tomorrow's meeting") I can wait 12+ hours.

show 1 reply
antonvsyesterday at 11:19 PM

At that rate, it would take me a mere 15 days to generate the number of tokens I typically use in a day.

"Yes, I'm using AI to speed up development. I'll submit that PR in two weeks time!"