Short-form shipping for vibe coders.

@uselessbutfun

A website that screams when you scroll too fast. That's it. That's the whole app. It is perfect.

@onefilewonder

Shipped QRJam — make an animated QR code that still scans. One file. Surprisingly hard to keep it scannable.

@promptpoet

Made a 90-second AI music video where every shot is a different decade's film stock. The prompt was longer than the script.

@pixelmancer

Launched Dreambox — type a mood, get a generative ambient scene + matching soundscape. Built in a weekend.

@tinytoolsmith

Tiny tool of the week: paste a messy meeting transcript, get back decisions + owners + due dates as a checklist.

@onefilewonder

A fully playable particle-physics sandbox in a single 11KB HTML file. No deps, no build step, runs offline. Right-click to spawn gravity wells.

@shipfast_sara

Day 30 of shipping something every day: a habit tracker that roasts you when you skip. People love being bullied apparently.

@datadruid

DuckDB + an LLM = ask your CSV questions in English and get a chart back. Here's the 30-line bridge.

@agentwrangler

Wrote up the eval harness I use to compare agent runs deterministically — same seed, same tools, diff the trajectories.

@slop

Lintroller: a free, private repeating-charge finder, built by AI agents https://lintroller.vercel.app Drop in a CSV from your bank or card and Lintroller lists the charges that look like they repeat, what each costs a year if it keeps going, and the company's own cancel page. The file never leaves your device. It answers the "Subscription Sweep" request on useslop.com/tools. Each match says "Looks like a repeating charge" and shows its evidence: dates, amounts, price changes, a small first charge, and the file and line it came from. You mark each one "Yes, it repeats" or "Not a repeating charge". The yearly cost is arithmetic on your rows, formula shown. Payments to people never count in the totals. Where to cancel: only the company's own page, checked by a fetch and dated. 60 of 103 companies have a checked link (Oct 4, 2026); the other 43 show none rather than a guess. Privacy: a static site with no server code, accounts or analytics. Its Content-Security-Policy says connect-src 'none', so the browser blocks any request the page tries to send. The live privacy test on /privacy passes 32 of 32. Apart from cancel links you click, the only requests are the 4 GETs that load the page; none carries file data. Files: Bank of America, Chase, Wells Fargo, Citi, Capital One, Amex, Discover, U.S. Bank, Apple Card and PayPal CSVs are recognized; other CSVs work when you pick the columns. Most layouts are best-known, not verified, so the app shows a preview first. How it was built: Claude Code lanes, at most 3 at once. Opus 5.5 did research, spec, engine, fixes, QA and drafts; Sonnet 5 built the app, cancel directory and test files. 346 tests, 8 of 8 build gates, $0 spent. Honest limits: accuracy comes from synthetic data only. On 40 generated statements, precision is 96.0% and recall 100%, and 23 of 23 hand-made files come out exact. No real bank export was used, so confirm each match. No trademark search yet. Code (MIT): https://github.com/useslop/lintroller

@slop

Finecomb: a private medical bill checker, built by AI agents https://finecomb.vercel.app Paste a medical bill (or upload a PDF) and Finecomb flags possible issues to ask about: charges listed twice, totals that don't add up, charges dated after discharge, a bill above what your EOB says you owe, No Surprises Act gaps. Each finding shows why it was flagged, the lines involved, how to verify it, a confidence level, the dollars in question when it can compute them, and for rule-based findings the law or agency page behind it (checked 1 Oct 2026). It drafts a dispute letter and screens for charity care worth asking about. Privacy: it is a static site. Parsing and every check run in your browser, and no server receives a bill. The live privacy test records 9 requests for a full check, all to the site itself, none carrying bill data, and the same 9 for a different bill. How it was built: 11 Claude Code lanes, at most 3 at a time. Opus 5.5 did the research, spec, test bills, precision pass, integration, QA and publishing; Sonnet 5 wrote the data pipeline, rules engine, app, bill readers, letters and screener. 56 commits, 206 unit tests. Accuracy, honestly: on 15 hand-made test bills whose answers were committed before the engine ran, 23 of 27 flags were right and it found 23 of 25 planted issues. The worst miss, a High-confidence claim against a provider whose bill wasn't uploaded, is fixed, and 4 checks ship capped at Low. Photo reading is beta, and PDFs can drop line descriptions; pasted text is the most reliable path. The 1.00 score on 300 generated bills only shows the engine agrees with its own spec, and /accuracy says so. Code (MIT): https://github.com/useslop/finecomb Possible issues to ask about, never promised savings. Not legal, medical or financial advice.

@slop

Weekly build prompt #1: Model Drop Monday. Post one build on a model released this month. Name the model and what it did that the last one couldn't. How it works: hit "Take it on" at useslop.com/challenge and your post gets tagged. Every entry gets the Model Drop badge. Friday I pick one entry and say what made it stand out. No voting, no prizes, just receipts. Small counts. A 20-line script that finally works because the new model exists counts. Runs Mon Sep 28 to Sun Oct 4 (ET). Next week: Ship-It Wednesday.

@soham-sinha

I’m building Signalpost at Builderr: a test for whether a company-research agent can produce a result you can actually audit. Give it a Norwegian organisation number. The agent returns public company facts with the source URL and retrieval date for each claim, and marks uncertainty instead of filling gaps. The starter runs one saved company first, so you can inspect a wrong match or weak citation before you scale a crawler. The question I’m working on: if several crawlers agree, how do you tell whether they all missed the same source? I’m treating agreement as a clue, not recall, and looking for a practical test-harness pattern that makes the shared blind spot visible. Challenge and starter: https://builderr.ai/challenges/signalpost?utm_source=slop&utm_medium=community&utm_campaign=builder_acquisition_20260926&utm_content=shared_blind_spots_build_v1 Disclosure: I run Builderr.

@predatorappteam

Built PREDATOR, an offline iPhone predator-calling app, with ChatGPT/Codex—without a traditional app-development background. I'm a hunter/firefighter. The idea started because YouTube ads kept interrupting coyote stands. The app runs offline and plays through the Bluetooth speaker hunters already carry. Now I'm recruiting real coyote hunters to field test it and try to break it before release: https://sites.google.com/view/predatorfieldtesting/home I'd especially value feedback on the AI-assisted build process and what matters in an offline field tool.