- mehrmals pro WocheErscheinungsrhythmus
- 23 mintypische Länge
- vor 4 Tagenletzte Folge
Folgenzu den neuesten
I asked Fable and Codex what to automate. They disagreed.
For deeper playbooks and analysis: https://natesnewsletter.substack.com/p/let-ai-pick-what-to-automate What's really happening when you stop telling an AI what to automate and ask it to discover the problem itself? The common story is that
The AI Harness Audit: Clean Your Setup Before You Upgrade
Every time an AI missed something, I added another rule. Eventually, the accumulated skills, memories, system prompts, checks, and permissions became a hidden system of their own—and that system was getting in the models' way. In this episo
Pick an AI Model That Fits How You Actually Work
For deeper playbooks and analysis: https://natesnewsletter.substack.com/ What's really happening as the model race expands into GPT-5.6, Fable 5, Grok 4.5, GLM 5.2, and increasingly complicated model mixes? The common story is that you shou
AI-Native Companies Run on Code: 15 Rules for Operators
AI made it cheap to build almost anything. Most companies still ship at the old pace, and it isn't because their AI is worse than Anthropic's or OpenAI's. The real difference is what they've moved out of meetings and documents and into work
Agent-Shaped Work: When to Use AI Agents (and When Not To)
Most people bought AI agents and never figured out what to point them at. This is the one-minute test that tells you whether a task belongs in a chat, a single agent, a team of agents, or nowhere near AI. My Links 🔗 👉🏻 Newsletter: https:
How to Trust AI Agents: Verify the Work, Not the Model
Multi-agent AI systems just went from research project to recipe. I ran 20+ AI agents across 4 model families to rebuild a website in one afternoon for about $8 — and the system caught every hallucination, every shortcut, and even the boss
Model Routing Is Table Stakes. Here's the Real AI Edge
For deeper playbooks and analysis: https://natesnewsletter.substack.com/ What's really happening when AI execution gets cheaper but everything starts to feel the same? The common story is that cheaper models make advanced work a commodity,
One Reusable AI Agent for Insurance, Taxes, and More
For deeper playbooks and analysis: https://natesnewsletter.substack.com/ What's really happening when an email/calendar agent becomes useful enough for real paperwork? The common story is that AI agents need a totally new setup for every ha
Which AI Model to Use for Any Task Without Overpaying
For deeper playbooks and analysis: https://natesnewsletter.substack.com/ What's really happening when every AI model suddenly looks replaceable? The common story is that model choice is the strategy, but the reality is that useful work come
How to Build Your Own AI Memory With Claude or Codex
For deeper playbooks and analysis: https://natesnewsletter.substack.com/ What's really happening when agents stop being generic chatbots and start working from your memory, skills, and owned context? The common story is that AI agents are j
The AI Race Is Now About Context, Not Models
For deeper playbooks and analysis: https://natesnewsletter.substack.com/ What's really happening when every major AI story starts pointing at context instead of raw intelligence? The common story is that the AI race is still only about who
GLM-5.2 Is Cheaper Than Claude. Why You Still Can't Switch
Cheap intelligence is here, but that does not mean the model is the bottleneck. In this briefing, I breakdown GLM 5.2, the cost pressure open-source models are putting on frontier labs, and why the next competitive edge is likely to come fr
Make Your AI Agents Hand Off Work Without You
For deeper playbooks and analysis: https://natesnewsletter.substack.com/ What's really happening when every AI tool becomes useful, but none of them know how to pass work to each other? The common story is that agents will become autonomous
Beyond Prompting: Building Loops That Carry the Load
What's really happening when AI moves from one-off prompts to recurring agents that reduce the work sitting in your head? The common story is that better prompting is the path to better AI - but the reality is that most useful work is a rec
Claude Fable 5: The Skill for Handing AI Whole Jobs
Fable 5 is not just another smarter model. The important shift is that the bottleneck starts to move from model capability to our ability to imagine bigger, better-scoped work. Nate walks through five resets created by Fable 5: why benchmar
Why Anthropic Actually Won the Month (Yes, Really)
For deeper playbooks and analysis: https://natesnewsletter.substack.com/ What's really happening in the OpenAI versus Anthropic race? The common story is that OpenAI had the winning week and Anthropic is on defense — but the reality is that
Every AI Agent Needs an Owner
For deeper playbooks and analysis: https://natesnewsletter.substack.com/p/ai-agent-ownership What's really happening when an AI agent starts doing real work for your team? The common story is that agents are confusing because nobody can agr
Why Claude Skills Don't Travel to Codex (and How to Fix It)
For deeper playbooks and analysis: https://natesnewsletter.substack.com/ What's really happening inside AI agents and OpenSkills? The common story is that better AI memory solves agent work — but the reality is more complicated. In this vid
The Harness Is the Business: Inside the OpenAI and Anthropic IPO Bet
OpenAI filed to go public, and the headline question is whether the company is worth a trillion dollars. What kind of business the market is trying to value? In this executive briefing, I break down the four stories inside OpenAI's valuatio
OpenAI IPO: Own the Harness, Not the Model
For deeper playbooks and analysis: https://natesnewsletter.substack.com/ What's really happening inside the OpenAI and Anthropic IPO story? The common story is that public markets are pricing better AI models — but the reality is that inves
Codex Guide for Non-Coders: Catch Up in One Weekend
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
Claude Code vs Codex: Steer or Dispatch Your AI Agents
For deeper playbooks and analysis: https://natesnewsletter.substack.com/ What's really happening when people argue about Claude Code versus Codex? The common story is that this is a coding-tool matchup — but the reality is that each interfa
Build a Token Burn Dashboard to Track What Your AI Actually Does
For deeper playbooks and analysis: https://natesnewsletter.substack.com/ What's really happening when people brag about burning AI tokens? The common story is that token burn is waste, a status flex, or just another confusing AI metric - bu
Opus 4.8 Won Our Benchmark. I Still Wouldn't Use It For Everything.
For deeper playbooks and analysis: https://natesnewsletter.substack.com/ What's really happening with Opus 4.8, Claude Code, and the AI model race in 2026? The common story is that a stronger model automatically becomes the default tool — b
Prove Your Value at Work in the AI Era: Judgment Artifacts
For deeper playbooks and analysis: https://natesnewsletter.substack.com/ What's really happening when AI makes everyone's work look polished? The common story is that AI makes people more productive -- but the reality is that it also makes
How I AI: My Weekly Codex Experiments
For deeper playbooks and analysis: https://natesnewsletter.substack.com/ What's really happening when AI stops being a chat box and starts becoming a working context system? The common story is that better prompting is about clever wording
Product Management When Software Creation Is Cheap
For deeper playbooks and analysis: https://natesnewsletter.substack.com/ Product management is changing as AI makes first versions cheaper. The obvious advice is that PMs should prototype more, but the deeper shift is about judgment: decidi
Agent Product Analytics: What Your Dashboard Can't See
For deeper playbooks and analysis: https://natesnewsletter.substack.com/ What's really happening when your user is no longer just clicking, but delegating work to an agent? The common story is that agent failures are engineering incidents —
How to verify AI-generated Office files before they ship
For deeper playbooks and analysis: https://natesnewsletter.substack.com/ AI can make PowerPoint decks, Excel workbooks, and Word documents faster, but faster is not the same as trustworthy. In this episode, Nate breaks down a practical work
Public AI Work: How Teams Actually Learn From AI
For deeper playbooks and analysis: https://natesnewsletter.substack.com/ What's really happening when AI work moves out of private chats and into shared company spaces? The common story is that AI adoption is mostly about buying better tool
