top | item 43842510 (no title) practice9 | 10 months ago Well the system prompt is still the same for both models, right?Kinda points to people at OpenAI using o1/o3/o4 almost exclusively.That's why nobody noticed how cringe 4o has become discuss order hn newest astrange|10 months ago They have different uses. The reasoning models aren't good at multi-turn conversations."GPT-4.5" is the best at conversations IMO, but it's slow. It's a lot lazier than o4 though; it likes giving brief overview answers when you want specifics. whimsicalism|10 months ago people at OAI definitely use AVM which is 4o-based, at least
astrange|10 months ago They have different uses. The reasoning models aren't good at multi-turn conversations."GPT-4.5" is the best at conversations IMO, but it's slow. It's a lot lazier than o4 though; it likes giving brief overview answers when you want specifics.
astrange|10 months ago
"GPT-4.5" is the best at conversations IMO, but it's slow. It's a lot lazier than o4 though; it likes giving brief overview answers when you want specifics.
whimsicalism|10 months ago