←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: 0.254s | source
Show context
jonplackett ◴[12 Apr 25 12:27 UTC] No.43663801[source]▶
I’m still really surprised everyone loves Gemini 2.5 so much.

Even for coding I find GPT4o to be more concise and write more sensible things.

I get the one-shot ‘build me a flight simulator’ type thing is special to Gemini 2.5 - but who actually ever uses it that way?

I feel a bit old school for aging it, but I still prefer ChatGPT at this moment. Am I the only one?

replies(1): >>43664402 #
1. thebigspacefuck ◴[12 Apr 25 13:56 UTC] No.43664402[source]▶
If you’re not using something like Cline or Cursor you should give them a try.

I haven’t found any OpenAI models good for agentic coding. o3-mini and 4o were both worse than 3.5 Sonnet. 3.7 and Gemini 2.5 Pro both seem be better than 3.5. I still use 4o with search as my primary reference model though.