(openai.com)

555 points maheshrijal | 1 comments | 16 Apr 25 17:01 UTC | HN request time: 0.233s | source

Show context

typs ◴[16 Apr 25 17:13 UTC] No.43707854[source]▶

I’m not sure I fully understand the rationale of having newer mini versions (eg o3-mini, o4-mini) when previous thinking models (eg o1) and smart non-thinking models (eg gpt-4.1) exist. Does anyone here use these for anything?

replies(2): >>43707901 #>>43707916 #

1. sho_hn ◴[16 Apr 25 17:16 UTC] No.43707901[source]▶

>>43707854 #

I use o3-mini-high in Aider, where I want a model to employ reasoning but not put up with the latency of the non-mini o1.

↑

OpenAI o3 and o4-mini