TECHNIQUE
Have your agent grade how risky a PR is to merge.
Free. One email a day. One-click unsubscribe.
Have your agent grade how risky a PR is to merge.
skillbox is open source under MIT. It gathers your scattered markdown skills into one place.
A launcher that ranks by intent. Type "the pdf I just downloaded" and the newest PDF is the top hit on every keystroke.
Every line is our summary. Every link goes to the person who did the work.
Have your agent grade how risky a PR is to merge. It asks whether the change can be reversed and how much breaks if it's wrong, so you know where to spend review time.
How an agent should compact its context. Compaction keeps the agent focused. It isn't a noise filter, and it should run rarely.
Coding without managing sessions. He sends thoughts as they come, the project splits them into threads, and he shows his actual prompts from the day before.
Shared memory for parallel coding agents, from an NVIDIA paper. Every result is an immutable Git commit, so agents build on verified work and stop repeating each other.
skillbox is open source under MIT. It gathers your scattered markdown skills into one place. Don't read the readme. Ask your agent to set it up.
Jev is on OpenRouter in beta. You send app state and a typed question. It returns a typed decision with a probability, and there's nothing to parse.
What Jev is, and nine things developers wired it into within 72 hours of launch.
A launcher that ranks by intent. Type "the pdf I just downloaded" and the newest PDF is the top hit on every keystroke.
They gave an agent a company card and told it to make money. It ran cold outreach, built payment pages, and made $75.
A weekend project to keep every skill, plugin, and key in one place, so switching between agent platforms costs nothing.
The feed rewards whatever gets replies. We review for what you can use on Monday. Most of what we read doesn't make it, and that's the service.
Engagement bait. The most-engaged post in our panel one morning was about a tennis star’s sneaker equity. Good story. Not for this list.
Hype. Claims that everything changes, with no steps, numbers, or code behind them.
Announcements you can’t try today. Waitlists, teasers, and "coming soon".
Arguments about who’s winning. Lab against lab, model against model. Entertaining, and it won’t ship your project.
No algorithmic timeline and no trending tab. One fixed list of people, one written rubric, and the same standard every day.
Builders, researchers, and founders who ship in public, chosen by hand. We read all of what they post, not what an algorithm surfaces.
A model reads each post against a written rubric and scores it from 0 to 3. Popularity isn't an input.
Technique, tool, or build. We write one line on each and link to the original, so the author gets the click.
Pure vibes, a take, or an abstraction.
An opinion or observation without support.
A specific claim, example, or firsthand detail.
Numbers, steps, code, or checkable evidence.
The pass line sits between 1 and 2.
No paid tier and no locked archive. One sponsor per issue pays for the reading.
Ten reviewed posts every morning, and every past issue in the archive. No account needed.
One sponsor slot per issue, written by us in the same plain voice and clearly marked. It never sits inside the ten.
No. Each line is our own summary, and each one links to the original on X. If you want the detail, you read it from the author.
Partly, and we say which part. Jev, a small model built for judgment calls, grades every post against the rubric. A language model then writes the ten one-line summaries. No person edits an issue before it goes out, so every line links to the source.
328 accounts picked by hand for shipping real work in public. People come off the list when they stop building and start broadcasting.
Because you'll read ten. A list of fifty is a second feed.
Free. One email a day. One-click unsubscribe.