But it can’t do audio in/out or image out. Feels like an architectural step back... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		ComputerGuru 7 months ago \| parent \| context \| favorite \| on: GPT-5 for Developers But it can’t do audio in/out or image out. Feels like an architectural step back.

conradkay 7 months ago [–]

My understanding is that image output is pretty separate and if it doesn’t seem that way, they’re just abstracting several models into one name

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact