logoalt Hacker News

timrtoday at 6:30 PM2 repliesview on HN

If they didn’t constantly reset, they’d be about the same as Anthropic.

Right now, I find that Grok offers better value, uses fewer tokens per turn, and makes better code. I haven’t tried Cursor because I don’t want to change editors again, but maybe I should try it…


Replies

apitmantoday at 6:41 PM

Are there any projects that track how much usage of each model translates to how much percentage drop in weekly/5hr windows?

show 2 replies
esafaktoday at 7:10 PM

That is not true; GPT is the most reasoning efficient model family on the market.

show 1 reply