Inside OpenAI DevDay: superhuman computer use, Decisions API, and the AI cloud
Latent Space · youtube · 2026-10-01
Latent Space hosts OpenAI's Ari Weinstein (Computer Use) and Nikunj (API team) right after DevDay. Key points:
Computer Use
- Ari says Computer Use is "180 degrees different" from months ago; some real-world tasks now complete faster than the average human
- Dots gives every agent its own Linux cloud computer
- Speed comes from combining screenshots, accessibility trees, the DOM, Playwright, and generated code
- Agents now debug and recover from failures; the goal is literally superhuman software operation
Developer stack
- Async tool calling means models keep reasoning while tools run
- Mid-turn steering, WebSockets, GPT Live for real-time control
- UltraFast inference; Decisions API as low-latency structured decisions, already used internally for support classification
- Longer prompt caching, cache pre-warming, server-side compaction for long-running agent threads
- OpenAI's inference teams use coding agents to optimize their own systems
Big picture: whether OpenAI is building an "AI cloud" with higher-level primitives for agents — memory, compute, state — plus trust, permissions, and safety when agents can make payments.
More from coding & agent
- Google Launches Gemini 4 Argon, Claims SOTA on Long-Horizon Software Engineering — lmthang · 2026-10-01
- Developer review: Muse is good but the agent is slow, dumb, and battery-hungry — ivan_bezdomny · 2026-10-01
- Dev Builds a Minimal Coding Agent From Scratch, With Session Branching and Compaction — nik-55 · 2026-10-01
- Cognition First to Run NVIDIA Vera Rubin on CoreWeave, ~4.8x Throughput vs GB200 — silasalberti · 2026-10-01
- Astra ultrafast rebuilds an app from scratch in ~3 mins using 10% of a $500/mo plan — OpenAIDevs · 2026-10-01
- ChatGPT's 'Dot' Can Spin Up Its Own Threads and Message Them Proactively — daniel_mac8 · 2026-10-01