Workflow

Yesterday (June 23) Anthropic published Introducing Claude Tag on the Newsroom. The post is short, but somewhere in the middle there’s a line I read twice: Today, 65% of our product team’s code is created by our internal version of Claude Tag. Sixty-five percent. Of the code Anthropic’s own product team writes, 65% is written by Claude Tag. The source matters here. This isn’t a customer case study. It’s Anthropic dogfooding the thing, then publishing the number. It’s the same release pattern they used for Claude Code Artifacts on June 18. Anthropic ships only after the workflow has been chewed on internally long enough to be embarrassing not to. ...

I almost tweeted the Fable 5 launch post yesterday afternoon. Karpathy called it a “major-version-bump-deserving step change forward.” Alex Albert, Boris Cherny, Thariq, Garry Tan — all in. The first two stories on Hacker News were Fable derivatives. The timeline was begging me to do it. Then I opened the GitHub monthly leaderboard. mattpocock/skills added 56k stars in a month and cracked the top five.¹ Leonxlnx/taste-skill (a skill that teaches your AI taste) and hardikpandya/stop-slop (a skill that removes AI tells from prose) hit the same monthly chart the same month.² ³ Not one of them has “Fable” in the name. None of them are riding the model hype. They all do the same thing: make what the AI writes faster to review. ...

If someone asks me how a normal person should understand Claude Code and other coding agents, I would not start with code. I would start with a much simpler picture: put a pile of PDFs, screenshots, spreadsheets, meeting notes, and transcript files into a folder, then ask the agent to read them, write scripts where needed, and produce an HTML report you can actually open and inspect. That does not sound like “programming.” ...

Some tools are not exciting. They are just useful in a way that quietly becomes hard to live without. Zara Zhang recently recommended a Mac utility called Amphetamine. Its job is simple: keep your Mac awake when the lid is closed, while a file is downloading, while an app is running, or during a long task. That sounds almost too small to write about. But I think it points to a very real shift in personal workflows: our laptops are starting to behave less like devices we actively sit in front of, and more like small personal servers. ...

I am increasingly convinced that the real significance of AI agents is not that they are “yet another tool that can chat.” It is that they are quietly changing the smallest unit of work. In the old model, if you wanted to scale what one person could do, the first move was usually to hire someone. Now the first move is often different: break the workflow apart, delegate the automatable pieces to agents, then keep yourself in charge of judgment, coordination, and final review. ...

I’m more and more convinced of one thing: AI video is heating up again not because models suddenly learned how to make films, but because the input layer changed. For a while, everyone treated prompt writing like a contest. You had to know shot language, pacing, style cues, and how to avoid broken hands, broken faces, and broken subtitles. That works for power users. For everyone else, it gets old fast. People are not here to take a prompt exam. They are here to ship content. ...

I increasingly think the most important race in AI video is not who understands prompts better. That may sound odd. For the past two years, AI video has been almost inseparable from prompting: how to describe camera movement, how to specify style, how to keep characters consistent, how to avoid broken hands, fake text, and weird cuts. People who write better prompts do get better results. But that is also the problem. ...

A line I saw this week was a little too accurate: the problem right now is not that we do not have enough agents. The problem is that we do not have enough work to give them. The original post came from Zara Zhang: https://x.com/zarazhangrui/status/2046662237306421608 I laughed when I first read it, not because it was exaggerated, but because it felt uncomfortably close to the truth. To avoid hiding the sources behind linked anchor text only, here are the primary source URLs up front: ...