Every 📧's banner
Every 📧's profile picture

Every 📧

@every53,028 subscribers

The only subscription you need to stay at the edge of AI. Ideas and apps: @TrySpiral @CoraComputer @SparkleApp @usemonologue

Shorts

AI writing can sound robotic. But it doesn’t have to. Enter: Compound Writing. Most people use AI for writing like a vending machine: one prompt in, finished piece out. Then they're disappointed when it doesn't sound like them. Katie Parrott uses AI to write every day, but she doesn’t let it draft a whole piece for her in one shot. Before she drafts, the model interviews her with 15-30 questions to draw out her thinking. Then it outlines, drafts, and reviews with her, one section at a time. When a session teaches her something worth keeping, she saves it to her voice and style files. The next piece gets a head start. She packaged the whole process as a free open-source plugin for Claude Code and Codex, with reviewer personas like /hitchcock (does the reader lean in?) and /sorkin (does it move?). Compound Writing, the ultimate guide:

AI writing can sound robotic. But it doesn’t have to. Enter: Compound Writing. Most people use AI for writing like a vending machine: one prompt in, finished piece out. Then they're disappointed when it doesn't sound like them. Katie Parrott uses AI to write every day, but she doesn’t let it draft a whole piece for her in one shot. Before she drafts, the model interviews her with 15-30 questions to draw out her thinking. Then it outlines, drafts, and reviews with her, one section at a time. When a session teaches her something worth keeping, she saves it to her voice and style files. The next piece gets a head start. She packaged the whole process as a free open-source plugin for Claude Code and Codex, with reviewer personas like /hitchcock (does the reader lean in?) and /sorkin (does it move?). Compound Writing, the ultimate guide:

148,859 次观看

It's Christmas morning: OpenAI and Anthropic shipped new models on the same day! We tested GPT 5.3 Codex vs. Opus 4.6 head-to-head. Verdict: the models are converging. Here’s what we found 🧵

It's Christmas morning: OpenAI and Anthropic shipped new models on the same day! We tested GPT 5.3 Codex vs. Opus 4.6 head-to-head. Verdict: the models are converging. Here’s what we found 🧵

11,975 次观看

Videos

没有更多内容可加载