logoalt Hacker News

aleccoyesterday at 2:31 PM1 replyview on HN

This guy tested it: https://she-llac.com/claude-limits

"Suspiciously precise floats, or, how I got Claude's real limits" 19hs ago 25 points https://news.ycombinator.com/item?id=46756742

OTOH, with ChatGPT/Codex limits are less of a problem, in general.


Replies

esafakyesterday at 3:45 PM

Because Codex effectively rate limits you by being so slow.

show 1 reply