Re:Claude 3.5 Sonnet
by Davidzheng on Thursday June 27, 2024 @01:11AM
(#40807461)
The thing is, gpt4(o) is the only model I've talked to that makes me feel like it understands calculus. Not like it's pretending and succeeding
Ah, I think it's just much better trained. At double the speed and half the price, I'd assume there's less computing power behind it. But likely the training covers some topics really well.
My answer from gpt4o was correct and similar to your example from claude. Maybe you were just unlucky?
This kind of thing happens so frequently that I don't think so. My guess is the language auto detection messes it up for multilinguals and it works fine for people who are solely using English? Because it's certainly broken on voice input - I ask it a question in English and it will respond in Russian and such.
gpt-4o: "Yes, 400,000 is the same as 4 X 100 × 1000."
gpt-4:
claude-3.5: Everyone keeps saying gpt-4o beats benchmarks and stuff, but this is consistently my experience with it. The benchmarks fall far off my every day experience.