A random mix from the whole library. Shuffle for a new set.
His role was eliminated on Tuesday morning. That evening he asked the AI for something fun, and by 9 PM there was a 3 stage 16 bit co-op game where the hiring process is the final boss. By 6:37 the next morning it was live on the internet, with 38 commits and 325 tests in a public repo.
He found a problem on his website with the embedded Cal.com widget he uses for people contacting him. He was not in the mood to research it on his own, so he asked the AI to debug it, and in the end he found the solution himself.
The AI connected to the user's VPS over SSH, ran a health check and applied updates, all directed from the couch.
Weekly Chezmoi drift report across all his machines, including what he changed, set up in 30 minutes.
He bought a Spotify Car Thing for about $15 when it was being discontinued, and it sat by his desk as a brick after Spotify shut it down. Today he had the AI help him turn it into a little touch screen companion.
Joao Silva installed the Jev decision-model skill into his AI fleet without writing integration code: he pasted a plain-English instruction into a session and the agent copied the folder, found the right .env file, added the key and ran the checksum verification. The skill then passed his mandatory three-reviewer gate (security, QA, technical writing) before being committed.
He says he took pictures of his Lego sets and asked the AI to download the manuals and organize them into folders in his iCloud Drive. It worked great.
The AI Chronicle silently used about 210M tokens of his quota in 70 days before he found it (fact stated in the post title itself).
The AI made a PHP script that used the Google Photos API to pull all his photos to his archive location; the extraction is done.
A developer had the AI build mazkir, a shared-memory service: tell the AI something once and it appears in his next chat, in an AI app and even in an AI app, stored as plain Markdown notes. Launch week brought about 160 visitors and exactly one sign-up — his friend.
Had the AI build a minimal OTel agent sending VM metrics to a collector plus iOS and macOS apps to query it regularly; works with his existing setup at no extra cost.
Had an agent write an MCP for his SearXNG setup, then do comparison passes against server-side LLM web tools and tweak it; it works pretty well in his own search use.
The poster of the spam text case also had his bot remove his personal details from data broker listings. He lists both jobs among the things the bot has genuinely handled for him.
She uploaded the first 10 images by hand, adding each prompt as alt text. Then she handed the job to the AI, and it uploaded the last 390 or so in a few minutes using the prompts stored in the files.
Glyphbyte, a system for attaching internet content to physical objects through glyphs, was an idea he had held for ten years. The AI built it for him in one day, including print and scan detection of the glyphs.
A developer built himself an AI evening edition. It goes through the posts and articles he saved, checks each one against his actual setup, and sorts them into adopt, trial, park or skip. Any change it suggests waits for his yes. The first run cleared his whole backlog of 30 items, and a planted fake post with hidden instructions was flagged and skipped.
A maker had an LLM design a circuit board by running KiCad headlessly from a terminal, checking the design in a loop until it passed every rule check. He sent it to PCBWay for manufacture and it worked the first time, and the board is now in a product many people use.
His agent system makes podcasts for him. He told it to treat alternative sources with the same skepticism it applies to official ones. The shows now push back on everything, and he says he loves the result.
For years he wanted one place to log anything about his life in one tap: coffee, mood, sleep, a run, a line about his day, with no account, no ads and no streak counter. Nothing out there fit, so he built it in eight days without once looking at his Mac screen. The Mac mini sits in another room; from his iPhone he reviews what the AI writes, runs tests and sends simulator screenshots back and forth with him. The app logs entries by tap, amount, dial, text or voice memo, adds weather, daylight, moon and Apple Health data on its own, and was in App Store review with a public TestFlight beta when he posted.
The AI built a complex quiz web app for himself and friends with multiple question types, screen sync, media uploads and scoring, in about a week of evenings (build reported in-window; the comment's complaint about current models left aside).
Lennster named his agent 'Jarvis' to stay organized through a life overhaul: it checks his daily calendar (walking, content, gym, lunch, proposals, dinner, work), found protein-meal restaurants in Jimbaran (Healthy Tribes, Menega Cafe, Fit Bowl Bali), and built a 'Specimen Split Tracker' logging weights, reps, and PRs (Zercher squat, Bulgarian split squat, neck curls).
He deleted his daughters photos from an SD card, and every Mac recovery tool he found would scan for free but charged $89 a year or $130 to $200 to actually save anything. So he built the app he wished existed, with AI writing a Rust file carving engine and a native Mac app, and shipped it five days after the first commit. It is now a paid app of its own, $29 once, no subscription.
Used nit-picking history-teacher agents to evaluate a few hundred generated stories for accuracy, and pointed the AI at HN comments to aggregate issues and fix them with his OK; reported issues mostly fixed.
He built a Word document of cheat sheets for 40 songs for a gig the next day, each song title in Heading 1 style with the lyrics and chords below. He told the AI to sort the pages by that heading text, keeping the text as it was, and the AI could not do it. He says the graphics in the document block the sort.
He set up a chain from his phone to the AI to his Windows PC and a background browser. The PC published a post to Bluesky and checked it had gone up, while his other screen work kept running separately.
A voice agent called 12 venues for his event of about 50 people and asked each one the same three questions. The AI then formatted the answers into a comparison table, which saved him an afternoon of phone calls.
He gave the AI the job of designing a 3D printable gearbox that connects to his camera lens, and it worked the first time. In the same post he notes the AI needed two tries at a simple joke answer.
He found the GPX file from his 2013 Mongol Rally, 437 kilobytes with 2,226 track points and 98 check in messages. After a flat map first to check the data, three rounds of prompting with AI turned it into an interactive 3D globe with every message pinned where it was sent and 99 photos placed along the 11,138 km route.
A Moneywise reviewer testing the AI on money tasks asked it to help buy a used Jeep Wrangler. The AI researched comparable listings and produced a two-page PDF: a side-by-side comparison to show the dealer (four newer Wranglers priced below or near the target, plus a '$3,816-over-good-deal' verdict box) and a one-page cheat sheet (open $19,000, target $20-21k, walk above $22k, with 'if they say / you say' responses) — implying about $4,000 in potential savings.
A man took the Amiga game he built in Baghdad in 1993, written in 68000 assembly, and had the AI Fable 5 read the code and port it to Godot. The port took an evening, a few more weekends got the feel right, and he released the original game for free alongside it.
Every idea is a real post from someone who tried it, summarized in our words, with a link to the original. App names are swapped for plain words.