Skip to content
Live nowSeason 2 · Episode 15 · Agentic Coding Guide

Season 2 · Episode 10

Fork the Camp

7 builds shipped in 30 minutes, live.

Listen on X ↗

The brief

Tonight we remix each other's work instead of starting from scratch. First 15 minutes: every builder picks one of their own past builds, decides they're willing to have it remixed, and drops the git repo in the Space. If you want to work on someone's build, it's on you to reach out to them and get access — they choose who they let in. Then fork it, ship a real improvement, and open a pull request against the original repo. Your submission is that PR: link it, say what you changed, and how you built it. Same clock as always — submissions open 8:30PM CST and close 9:00PM CST. Tonight's prize: $20.

What “Fork the Camp” meant

Every CampAI episode sets one theme and one constraint: 30 minutes, live, with AI doing the heavy lifting. Season 2's builders took “Fork the Camp” in 7 different directions — the submissions below are what actually shipped inside the window, with the models used and the problems hit written up by the builders themselves.

Submissions

Every build

Stemma — forked Ep.8 Rumor Mill so it measures memory, not paraphrase

by ₥AN$A · 36 ratings

A group passes one message down a chain. Each person sees ONLY what the last person handed them, then the app shows exactly how it mutated and who did it. The fork fixes three things in the Ep.8 build: 1. THE MESSAGE NOW DISAPPEARS. Before, it stayed on screen while you typed — so it measured deliberate paraphrase, not memory. Now you tap to reveal, get a countdown scaled to length (4-15s), the composer is LOCKED while it's up, then the text is removed from the DOM. Enforced server-side, so reloading isn't a free second look. Paste is blocked and typing speed recorded — a hop that comes back near-verbatim typed faster than anyone composes gets flagged LIKELY COPIED. 2. ONE BAD LINK NO LONGER POISONS THE RUN. Every claim used to be scored against the original seed, so one person going off-script marked every ribbon "dropped" and made the rest meaningless. Breaks are now detected (MAD outlier, robust to the single wild hop that inflates sigma), named, and the analysis re-baselines: per-segment fidelity, a second decay line, and a second flow diagram from where the chain actually restarted. Host can undo a turn. 3. THE BLINDING WAS BYPASSABLE. Player IDs were broadcast and join trusted a client-supplied one — you could read the host's ID off the wire, rejoin as them, and be handed the seed. Seats now carry a secret token, never broadcast. Live run from tonight: 13% survived against the original, 34% re-baselined after the break, break correctly attributed. The abduction called it "vividness, 78% confidence." The salience-5 detail (a cat asleep in a pastry box) outlived every other claim — textbook Bartlett sharpening.