Jason Liu shows how to run Codex as a long-lived computer-control agent
AI Engineer · youtube · 2026-07-24
Jason Liu explains how to set up Codex for long-running work
At OpenAI’s workshop, Jason Liu walks through Codex as a general computer-control tool rather than just a coding assistant. The talk focuses on:
- building a memory vault and assistant threads
- prompting Codex to collaborate across threads
- using computer use for broader task execution
- planning for long-running work streams and looped execution
The session is aimed at developers who want to use Codex, the Agents SDK, and the OpenAI API more reliably in production-like workflows.
More from coding & agent
- NVIDIA says Nemotron 3 Ultra hit 97.1% on agentic RTL chip-design tasks — NVIDIAAI · 2026-07-27
- Tokyo Agent Forge hackathon shipped production-ready AI agents in one day — DavidBennett__ · 2026-07-27
- Long-running agents will need immutable event logs, this thread argues — sebpaquet · 2026-07-27
- Agentic Data Science in Practice: Agents Write Code but Answer Wrong Questions — hugobowne · 2026-07-27
- A VS Code extension adds Markdown-style highlighting to Alchemy string templates — samgoodwin89 · 2026-07-27
- Claude’s Stripe MCP connector is being called unusable after repeated disconnects — evielync · 2026-07-27