Re:The 2025 AI Index Report
by slig on Thursday April 10, 2025 @01:23PM
(#43646119)
Was that on 3.7 Sonnet? I feel it's a lot worse than 3.5. If you can, try again but on Gemini 2.5.
[ Parent
| on HN ]
Re:The 2025 AI Index Report
by mrdependable on Thursday April 10, 2025 @01:30PM
(#43646188)
This was 3.7. I did give Gemini a shot for a bit but it couldn’t do it either and the output didn’t look quite as nice. Also, I paid for a year of Claude so kind of feel stuck using it now.
Maybe I will give 3.5 a shot next time though.
Re:The 2025 AI Index Report
by avandekleut on Thursday April 10, 2025 @01:27PM
(#43646163)
I'm glad I'm not the only one that has found 3.5 to be better than 3.7.
Re:The 2025 AI Index Report
by johnisgood on Thursday April 10, 2025 @02:26PM
(#43646756)
When did 3.7 come out? I might have had the same experience. I think I have been using 3.5 with success, but I cannot remember exactly. I may have not used 3.7 for coding (as I had a couple of months break).
3.7 came out on 24th February. My notes from that release: https://simonwillison.net/2025/Feb/24/claude-37-sonnet-and-c... and https://simonwillison.net/2025/Feb/25/llm-anthropic-014/
Re:The 2025 AI Index Report
by johnisgood on Thursday April 10, 2025 @04:29PM
(#43647759)
I will have to check, but apparently I have been using 3.5 with success, then. I will give 3.7 a try later, I hope it is really not that much worse, or is it? :(