add a heartbeat to the orchestrator and the subagents so if they stop they keep going when you do this be careful about the way the model ends it's responses with "here's what i'd do next…" sometimes that's helpufl, but if they're not working from a clear plan you can wake up
@danshipper
-
LLM Slop: Repetitive Words Across Different Contexts
By
–
one thing people miss about LLM slop is the slop is NOT in the actual words. it’s that the same words get used over and over in very different contexts. anything can be slop
-
Autonomous PR Deployment Using Codex Subagents in Production
By
–
prompt get many PRs to prod autonomously using codex subagents: Run a continuous prod-to-green swarm loop. Keep the immediate blocking task local. Use a small stable set of persistent subagent lanes:
1. prod monitor
2. staging shepherd
3. current/newest pathology investigator -
Subagents in Codex: Production Challenges and Value
By
–
i cannot tell you how valuable and impt subagents are in codex! last week i released a vibe-coded document editor, proof. the past few days have just been me fighting production bugs by copy-pasting log outputs and bug reports into new threads and then trying to manually
-
Autoresearch is powerful yet simple
By
–
guys, autoresearch is actually pretty amazing. it’s also a harsh lesson: ditch all your fancy agent infrastructure. just build the simplest possible system to throw more tokens at your problem.
-
Modèles IA évoluent vite, il faut tout réinventer souvent
By
–
this is pretty much the only way to build product in AI models move so fast, that you have to be willing to throw everything out every few months to take advantage of what's possible
-
Comparaison tâches planifiées entre Codex et Claude Code
By
–
tbh i have mostly been in codex app recently! i'd like to try scheduled tasks in claude code too, curious how it compares
-
Free Launch of Proof, Human-AI Collaborative Editor
By
–
— Dan Shipper 📧 (@danshipper) 11 mars 2026
I built a new product on the side while running @every—and today we're launching it for free. It's called Proof, a live collaborative document editor where humans and AI agents work together in the same doc. It’s built from the ground up for the kinds of documents…
-
Baseball Player Builds ML Pitching Analytics Platform with AI
By
–
I’m a baseball player. I’ve never written a single line of code in my life. But over the last few months, I used AI to build a pitching analytics platform from scratch. 8.9M pitches. Custom ML models. Total transparency. Here is a look at what happens when you give an
-
Barber Builds iPhone App for Attachment Style Coaching
By
–
My barber made and shipped an iPhone app that he and his friends are using to understand / help coach them on their attachment styles ! It takes a really long time for this stuff to filter down because you often need people who are starting from scratch to really adopt it You