All videos
0:00 / 0:00
ai

Inside OpenAI DevDay: Superhuman Computer Use, Decisions API, and the AI Cloud — Ari & Nikunj

Latent Space3 October 2026Watch on YouTube

What you'll learn

  • According to Ari Weinstein, Computer Use has changed 180 degrees in just a few months and can complete some tasks faster than an average human.
  • Dots gives every agent its own Linux computer in the cloud, opening up new possibilities for agents.
  • Modern Computer Use agents combine screenshots with accessibility data, the DOM, Playwright and generated code, and learn to debug and recover from failures themselves.
  • App Shots give models richer context than ordinary screenshots, and Computer Use closes the loop between writing software and testing it.
  • OpenAI is working on async tool calling, mid-turn steering, WebSockets, UltraFast inference, prompt caching and the Decisions API toward higher-level primitives for an AI cloud.

Frequently asked questions

What has changed about Computer Use in recent months according to the episode?
Ari Weinstein calls it 180 degrees different from a few months ago. The agents have become faster, cheaper and more reliable, can do some tasks faster than the average human, and are better at debugging and recovering from failures.
How does a Computer Use agent see and operate software?
By combining screenshots with accessibility data, the DOM, Playwright and generated code. App Shots give models richer context than ordinary screenshots.
What is the Decisions API and how does OpenAI use it internally?
The Decisions API goes beyond structured outputs at low latency. OpenAI uses it internally for things like support classification and other workflows.
Which developer API pieces are discussed in the episode?
Async tool calling, mid-turn steering, WebSockets, UltraFast inference, the Decisions API, prompt caching, pre-warming, compaction and the Agents API. This includes cache-aware applications and server-side vs manual compaction for long-running agent threads.

Topics

openaicomputer-useagentsapidevday

In this video

OpenAIOpenAI

Read next

Description from the channel

From giving AI agents their own cloud computers to making Computer Use faster than humans at real-world tasks, OpenAI is pushing agents much closer to actually operating software end-to-end. In this episode, recorded immediately after OpenAI DevDay, Ari Weinstein, who leads product and engineering for Computer Use, joins swyx and Vibhu to unpack Dots, GPT-6.1, the Agents API, App Shots, and the rapid improvements that have made Computer Use dramatically faster, cheaper, and more reliable. Ari explains why Computer Use is now “180 degrees different” from where it was months ago, how agents are learning to debug and recover from failures, why combining screenshots with accessibility data, the DOM, Playwright, and generated code changes the speed equation, and why the next frontier is making agents literally superhuman at using software. In the second half, Nikunj from OpenAI’s API team breaks down the new developer stack: async tool calling, mid-turn steering, WebSockets, UltraFast inference, the Decisions API, prompt caching, pre-warming, compaction, and the Agents API. He also shares the unusually fast story behind Decisions API, how OpenAI’s inference teams are using coding agents to optimize their own systems, and the bigger question of whether OpenAI is effectively building an “AI cloud” with higher-level primitives for agents, memory, compute, and state. We discuss: • Why OpenAI thinks Computer Use has changed dramatically in just the last few months • Dots and what changes when every agent gets its own Linux computer • Why Computer Use can now complete some tasks faster than the average human • The path from human-level to “literally superhuman” software operation • Why modern Computer Use agents are much better at debugging and recovering from failure • How screenshots, accessibility trees, the DOM, Playwright, and generated JavaScript work together • App Shots and why they give models much richer context than ordinary screenshots • Why Computer Use can close the loop between writing software and testing it • Trust, permissions, and safety when agents can make payments or operate third-party websites • Async function calling and why models no longer need to stop reasoning while tools run • Mid-turn steering, WebSockets, and the architecture behind more responsive agents • UltraFast inference and how OpenAI is pushing frontier models toward much lower latency • The rapid internal story behind Decisions API • Why Decisions API is more than just structured outputs at low latency • GPT Live, fast tool calling, and real-time computer control • How OpenAI is using Decisions API internally for support classification and other workflows • Longer prompt caching, cache pre-warming, and building cache-aware applications • Server-side compaction vs manual compaction for long-running agent threads • What should live inside an Agents API versus inside a developer’s own harness • OpenAI as an “AI cloud” and the search for higher-level primitives beyond raw model APIs Sponsorship and business inquiries: business@latent.space — Ari Weinstein • Head of Product & Engineering, Computer Use at OpenAI Nikunj Handa • Head of Product, API at OpenAI Timestamps 00:00:00 Hook 00:01:12 OpenAI DevDay: Dots, GPT-6.1, Agents API, and Decisions API 00:04:04 Dots and Personal Cloud Computers 00:06:11 Why Computer Use Is “180 Degrees Different” 00:07:16 From Sky to Self-Debugging Computer Use Agents 00:10:36 How Computer Use Sees and Operates Software 00:13:21 From Faster Than Humans to Superhuman Computer Use 00:17:15 Agents API: Trust, Permissions, and Safety 00:18:43 Computer Use for Coding, Testing, and QA 00:20:26 GPT-6 APIs, Async Tool Calling, and UltraFast Inference 00:24:33 The Rapid Story Behind Decisions API 00:26:44 What Decisions API Is and How It Works 00:31:36 What OpenAI Is Building With the New APIs 00:33:35 Prompt Caching, Pre-Warming, and API Performance 00:36:32 Context Compaction for Long-Running Agents 00:38:25 Memory, Higher-Level APIs, and the AI Cloud