
Read the full post on Substack: https://natesnewsletter.substack.com/Codex is changing how I work because it is not just giving me better AI answers. It is letting me hand real computer jobs to an agent: find the files, read the transcript, compare versions, render the artifact, check the result, and keep going until there is something real to inspect.In this episode, I walk through why the unit of work is changing, how my token dashboard became a receipt for agentic work, and why threads, goals, computer use, plugins, and skills matter for people who do knowledge work outside of code. The practical takeaway is simple: pick one annoying and valuable loop, give Codex sources, standards, boundaries, and proof, then learn how to verify what came back. Hosted on Acast. See acast.com/privacy for more information.
Podzilla Summary coming soon
Sign up to get notified when the full AI-powered summary is ready.
Free forever for up to 3 podcasts. No credit card required.

The Harness Is the Business: Inside the OpenAI and Anthropic IPO Bet

OpenAI IPO: Own the Harness, Not the Model

Claude Code vs Codex: Steer or Dispatch Your AI Agents

Build a Token Burn Dashboard to Track What Your AI Actually Does
Free AI-powered recaps of AI News & Strategy Daily with Nate B. Jones and your other favorite podcasts, delivered to your inbox.
Free forever for up to 3 podcasts. No credit card required.