“Thinking with Images” has been one of our core bets in Perception since the earliest o-series launch. We quietly shipped o1 vision as a glimpse—and now o3 and o4-mini bring it to life with real polish. Huge shoutout to our amazing team members, especially: - @mckbrando, for relentlessly improving infra & ML to lay the foundation (his o3/o4-mini livestreams are the best I’ve seen) - @ZhangZhshuai, for pioneering our next-gen perception architecture - @jilin_14, for baking in the strongest perception priors - @bowenc0221, for initiating and showing early signs of life in thinking with images - Jamie Kiros, for jumping in wherever work needed to get done - @dmed256 & @hthu2017, for heroic infra efforts -the Perception team, and everyone else at OpenAI who made it happen. Multimodal is critical to OpenAI's path to AGI, and join us to push the next frontiers!