←back to thread

Google is winning on every AI front

(www.thealgorithmicbridge.com)
993 points vinhnx | 1 comments | 12 Apr 25 03:58 UTC | HN request time: 0.289s | source
Show context
Lukman ◴[12 Apr 25 06:42 UTC] No.43661923[source]▶
In my experience Claude 3.7 is far superior for coding than Gemini 2.5. I tried it in Cursor and I wanted it to work, as a recent ex-Googler. I repeatedly found it inferior. I think it’s still behind Claud 3.5 for coding.

It would decide arbitrarily not to finish tasks and suggest that I do them. It made simple errors and failed to catch them.

replies(6): >>43661938 #>>43661985 #>>43661988 #>>43662194 #>>43662360 #>>43662583 #
jinay ◴[12 Apr 25 06:45 UTC] No.43661938[source]▶
Cursor is likely very tuned for Claude (prompts-wise and all) due to its dominance with 3.5 and now 3.7. Still, Gemini 2.5's tool calling has been pretty poor in my experience which Cursor heavily relies on.
replies(1): >>43663479 #
1. mjirv ◴[12 Apr 25 11:28 UTC] No.43663479[source]▶
Yep. Tool calling is terrible across all Gemini models. I’m not sure why, when the model itself is so good.