logoalt Hacker News

swyx04/02/20252 repliesview on HN

overall i REALLY like this paper and effort, but this part sounds like a bit of bullshit. they dont have the ability to implement retries and backoffs to deal with rate limits?


Replies

eightysixfour04/02/2025

Because they used wall clock time, not compute time, flops, or watts, to standardize. 24 hours and 36 hours of compute.

They could build a system which gives them equal compute time by ignoring time spent rate limiting and such, but they chose not to.

show 1 reply
moralestapia04/03/2025

"Why don't they just break the TOS"

Damned if you do, damned if you don't.