Three OpenAI Engineers Shipped A Million Lines. Your Ten-Hour Agent Run Starts Here.
AI agent context files are what keep a long agent run on track once your opening prompt goes stale. Here is how OpenAI, Anthropic, and Arize actually structure them, and the four files you can copy. Grab the Working Context Starter Kit on my Substack: https://natesnewsletter.substack.com/... My Links 🔗 👉🏻 Newsletter: https://natesnewsletter.substack.com/ 👉🏻 X: https://x.com/natebjones 👉🏻 TikTok: / nate.b.jones 👉🏻 Instagram: / nate.b.jones What's really happening inside a six hour agent run? The common story is that a bigger context window solves this, but the real question is which decision the agent treats as current. In this video, I share the inside scoop on progressive context shaping: Why one giant instruction file becomes a graveyard of stale rules How to change an agent's direction without restarting the project What four kinds of context you should keep separate Where OpenAI, Anthropic, and Arize put the current plan More capable agents extend the reach of your judgment, and they extend the reach of an outdated judgment exactly as far. Chapters: 00:00 The million line project and what the headline hides 02:43 OpenAI swaps the giant manual for a short map 03:21 Anthropic's progress file as portable memory 04:41 Progressive context shaping, defined 05:36 Why the opening prompt cannot stay in charge 07:04 Arize, 27 model calls, and the plan moved to disk 10:21 My Codex benchmark and the instruction that went stale 13:07 The four kinds of context worth separating 16:14 400,000 Claude Code sessions and the 70/80 split 17:15 Symphony, three to five sessions, and the ticket board 18:35 The four things to give an agent at the start 21:02 Why context window size is not the capability Listen to this video as a podcast. Spotify: https://open.spotify.com/show/0gkFdjd... Apple Podcasts: https://podcasts.apple.com/us/podcast...

OpenAI, NVIDIA And Anthropic Just Split. Here's How I'd Spend $20, $60 Or $200.

Your Chatbot Hallucinated in 2024. Your Agent Lies in 2026.

AI 2027 Plausible Future or Irresponsible Fear-Mongering? (Panel Review) Episode #34: AI 2027

Anthropic's Model Attacked Two Strangers On GitHub. Nobody Asked It To.

Two Ways Higher Ed and Continuing Ed Lose Enrollment in AI | ScaledOn Sessions

Anthropic's Boris Cherny: Why Coding Is Solved, and What Comes Next

Agents Aren't Taking Your Jobs. They're Creating More Work Instead.

The FDE Playbook for AI Startups with Bob McGrew

Claude Skills: I Stopped Installing Them. Here's What I Do Instead.

Most AI Labs are Simply Cooked | Jerry Tworek

If OpenAI And Anthropic Are Discouraging You, You're Probably A Level 1 Builder.

How to Build an AI-Native Services Company

Apple's New Mac Line is Built Around Local AI. The Bet Is You'd Rather Own Than Rent.

CLAUDE CODE ADVANCED FULL COURSE (3 HOURS)

Ilya Sutskever – We're moving from the age of scaling to the age of research

So You Learned Claude, Now What?

Andrej Karpathy: From Vibe Coding to Agentic Engineering w/ Stephanie Zhan

Andrew Ng: The Biggest Opportunities in AI Aren't Where You Think

AI Prompt Engineering: I Stopped Prompting One Task At A Time
