Vibeleaderboard
← All Intel
Intel / article

Unpacking ChatGPT Work: the Agent for a Billion Users

Source
latent.space
Author
Shlok Khemani
Date

Context

OpenAI’s ChatGPT Work suggested a meeting-preparation task before the user asked for one in this firsthand exploration. The author describes a suggestion drawing on calendar, email and personal , then producing a meeting brief after the suggested prompt was submitted. This illustrates a useful form of proactivity: identifying a task and assembling its starting context while leaving the decision to begin with the user. The account distinguishes these suggestions from separately configured scheduled tasks, which can run at an agreed time without a fresh prompt.

Key takeaways · AI-distilled
  • Work runs on the Codex inside a persistent cloud microVM (8 CPUs / 20GB RAM on Pro): the workspace syncs to persistent storage and is restored onto fresh isolated VMs, so the machine changes but working state carries over.
  • Each task gets a /workspace/scratch directory with real computer freedom — install dependencies, keep databases, write scripts — though the has far less sovereignty over its machine than an OpenClaw-style always-on box.
  • Web and mobile always run in the cloud; the desktop app adds a local mode that is essentially Codex with the coding UI stripped away, and local tasks do not sync to web or mobile.
  • Chat and Work sit side by side today but will merge by end of year (confirmed by Brockman) — Work is a preview of how ChatGPT's billion weekly users will use the app.
  • Artifacts are first-class output: sheets, docs and slides in interactive viewers, plus hosted Sites — web apps the agent builds, shares by URL, and keeps updated.
Terms in this piece · Glossary
  • context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
  • AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
  • MCP — The Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.
  • agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
Key quotes

“On July 9th, OpenAI released ChatGPT Work, their agent product for knowledge work.”

“None of this should detract from the fact that Work is an impressive, ambitious, yet underrated launch.”

Read the source www.latent.space
Recommended reads
Comments

Checking sign-in…

Loading comments…