Every article we published in September 2026.
Our tests show where it replaces Fable and Opus—and where we’re keeping the alternatives
Katie Parrott spent two years teaching AI to write like her. Now she’s sharing the system she built.Katie Parrott shares
Use AI to make better editorial decisions, and carry what you learn into the next story
OpenAI’s new model impressed us with writing, operating software, and visual design. Anthropic’s Fable still has better instincts for building a product.
I'm running 44 AI agents across multiple projects. Each one is just a model pointed at a folder.
Plus: Teaching AI to write like you, what Anthropic’s certification is good for, and 44 agents that are just folders
AI is ready to run your work in the dark. Don't let it turn the lights out in your head, too.
Five professional writers share how they use AI, where it disappoints them, and what they still insist on doing themselves
Why we’re building personal benchmarks for every employee, and how to start testing AI against your standards
Usage limits give my best questions—and my more questionable ideas—time to develop
Maggie Appleton and Kevin Roose on AI, personal benchmarks, and the Navier–Stokes proof
AI can turn work into play—and distract me from the work I need to do. Here’s how I’m learning to bring something back from those detours.
Plus: Mike's vibe check of a model that answers in probabilities; the computer chores our agents do for us now; and a workflow for making a solid deck with AI
Its new model turns fuzzy questions into probabilities fast and cheaply enough to check an AI agent’s work as it goes
How I went from ‘this is slop’ to work I’m willing to publish under my name
Plus: 13 beliefs about writing with AI, and an antivirus for the AI age
When expensive experimentation is worth it and when to rein in your tokenmaxxing
A professional creative studio puts GPT-6 to the test
Plus: A creative studio puts Astra to work on visual effects, 13 beliefs about writing with AI, and a Vibe Check of a new kind of model
Choose the best model for the work you do
Fable-level power at roughly 60 percent less than Fable’s token price makes Opus 5.5 impossible to ignore
Two models, one clear tradeoff
A look inside Mike Taylor’s writing workflow—and the work he still does himself
Why the classification model is blowing up your timeline, how to turn subjective questions into Jev checks, and the dawn of intent-based software
Plus: Where we stand on Grok 4.7, a workflow for going viral on social media, and why every company needs a Slack agent
Can Microsoft make workplace agents useful at scale?
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.
Katie Parrott
Kaushik Viswanath
Kieran Klaassen
Every Staff
Laura Entis
Jack Cheng
Mike Taylor
Cyrus Duff
Dan Shipper
Ryan Sloan