OpenAI's CUA leads on new agent stack: superhuman computer use, Dots cloud computers, Decisions API
OpenAIDevs · x · 2026-10-01
Latent Space's DevDay episode features OpenAI's CUA team leads Aran Komatsuzaki and Nikunj Handa pushing back on Dwarkesh's claim that computer use progress is slow:
- Computer use is already faster than humans on real-world tasks; better models can debug and recover from failures, and "grindability" matters as much as verifiability.
- Dots gives agents their own cloud computers for long-running autonomous work.
- Decisions API went from idea to shipped product in one week, positioned as a Jev competitor.
- An AI-native cloud: async tools, UltraFast inference, caching, compaction, and higher-level agent primitives are turning OpenAI's API into an AI-native cloud.
Related event: OpenAI Breaks Down Its New Agent Stack After DevDay(3 posts)→
More from coding & agent
- Generic API-catalog MCP server vs one tool per job: a context-bloat experiment — MandeepKaur9407 · 2026-11-16
- Berkeley paper: LLMs answer with stale values even when the update is in context — ombre-ai · 2026-11-16
- Effective HTML: 4.2k-star agent skills turn wireframes into self-contained interactive prototypes — tom_doerr · 2026-11-16
- skills-gate: one gate skill fronts 148 agent skills at just 389 tokens — Distinct-Pie2389 · 2026-11-16
- Open-weight Karpo-Decision-31B tops Decision Index at 73.9, one forward pass per answer — CodeByPoonam · 2026-11-16
- shadcn boosts @uisdk: one-shot UI rebuild that's instantly E2E-testable by AI — shadcn · 2026-11-16