We use analytics and advertising tools by default. You can update this anytime.
Manage optional tracking categories. Necessary cookies stay on so the site can function.
173 results for “codex”
After 24 hours of hands-on testing, we found a model that’s fast, reliable, and surprisingly funny—but still prone to overreaching and not yet a writing champ
Plus: Dan’s attempt to clone Kate, a shortcut for turning demonstrations into skills, and the human goals machines still need us to set
Why giving up manual coding made me more valuable, not less
A mini-Vibe Check on Gas City, a Grok classifier that grades your X drafts, and why HTML is the new markdown
A four-step engineering process for software teams that don’t write code
How to apply your expertise when AI absorbs the work
AGI is intelligence too valuable to shut off
Turning a list of my writing foibles into a skill that stops me from getting away with them
On the ground at the Microsoft Build conference with CTO Kevin Scott
Plus: The end of the AI subsidy, do you actually want to talk to your agent, and how to turn customer feedback into a product queue
A new home for learning AI in practice
Don’t do your work. Tend your loop.
Plus: An AI writing policy that makes writers do the thinking, Zuckerberg’s AI Future for Everyone runs on Meta, and a tool that keeps your agents from timing out
Anthropic’s new model crushes pull requests, research deep dives, and honest editing—yet o3 keeps the daily-driver crown
The company gets pragmatic in AI’s expensive era
The skills I transferred to my writing agent from playing Settlers of Catan
Plus: Our Claude Opus 5 Vibe Check, what makes an AI workflow stick, and the expertise trap that a prompt can’t shortcut
Five patterns from our Opus 4.5 Claude Code Camp you can apply today
The skills that make AI agents reliable are identical to the skills that make human teams effective
It’s launching today! Here’s our day-zero, hands-on report.