It's the naming. He is confusing 4o/4o-mini with o4-mini, the latter is a pretty strong model and it's also one of the newest. Oh and it's cheaper than the non-mini 4o.
It's the naming. He is confusing 4o/4o-mini with o4-mini, the latter is a pretty strong model and it's also one of the newest. Oh and it's cheaper than the non-mini 4o.
There's both a 4o and an o4? And they're different?
Yes. 4o is a non-CoT model that is the continuation of the GPT-4 line, itself superseded by 4.1. o4 is the continuation of the CoT model line.
There's also 4o-mini and o4-mini...
No, I meant 4o over o3. For a ton of people a reasoning model's latency is overkill for them asking for inspiration on what to make for dinner.
o4-mini isn’t really that great in comparison to o3, and I still use o3 as my daily driver for reasoning tasks. I don’t really have a purpose for o4-mini, not even for coding tasks.