Skip navigation
OpenAI's New Agent Stack: Superhuman Computer Use, Dots, Decisions API, UltraFast, & the AI Cloud
0:00 / 1:11

OpenAI's New Agent Stack: Superhuman Computer Use, Dots, Decisions API, UltraFast, & the AI Cloud

Latent.Space

@latentspacepod35K followers

Visit on X
99 likesDownloadOriginal post

25,711 views

OpenAI's New Agent Stack: Superhuman Computer Use, Dots, Decisions API, UltraFast, & the AI Cloud OpenAI’s Ari Weinstein and Nikunj Handa explain why Computer Use is already becoming faster than humans at real-world tasks, how Dots gives agents their own cloud computers, why better models can now debug and recover from failures, how Decisions API went from idea to product in weeks, and why async tools, UltraFast inference, caching, compaction, and higher-level agent primitives are turning OpenAI’s API into an AI-native cloud.

6 Comments

Comments from the original post on X (Twitter)

  • Kizuno18's profile picture

    @Kizuno18

    @OpenAI @AriX @nikunjhanda superhuman computer use speed only matters if action execution is coupled to accessibility tree state: raw coordinate clicks miss dynamic elements under fast renders. in our autonomous pipeline, executing actions against accessibility nodes keeps computer use 100% synchronized

  • Forge Orbital Inc's profile picture

    @forgeorbital

    @OpenAI @AriX @nikunjhanda Agent stacks keep getting more capable. The question regulated buyers ask next: what was this agent allowed to do, and can we prove it later? We built Forge for that: signed, replayable records on your own hardware. Would love to talk it through on the show.

  • Nikhil's profile picture

    @nikhilx22

    @OpenAI @AriX @nikunjhanda Dots versus Grok Bot versus Metamuse. Is gonna win?

  • EKOS _ AGI 🇮🇷's profile picture

    @OMID_0909

    The interesting part isn’t just that agents can now operate faster and recover from failures. It’s the amount of execution history this creates. Decisions, tool calls, failures, recoveries and verified outcomes can become a compounding advantage if they’re preserved as reusable knowledge. Otherwise every faster agent is still starting from zero. Do you agree? @sama

  • Oleg's profile picture

    @oleginprod

    @OpenAI @AriX @nikunjhanda my agents drive a real chrome. half their rules exist to slow them down

  • TobiasDev 🇦🇷's profile picture

    @0xTobiasDev

    @OpenAI @AriX @nikunjhanda computer use faster than humans plus agents with their own cloud, the stack talk is getting concrete