A random mix from the whole library. Shuffle for a new set.
An angler who designs fishing games used AI Build to make Bank and Boat, a free fishing game for phone and browser. It covers day tickets on UK canals, rivers, lochs and piers, and it is live now with no sign-in.
Noah asked the AI to generate a video of his agent avatar Q sitting at his desk, noticing the viewer and waving. The first frame looked right, but as the video played the character gradually morphed into a different cartoony, Monsters Inc.-style figure, and no retry kept the style or character consistent. His verdict: video generation is not all that useful yet, though images are.
She wrote an AI script that transcribes her French tutoring recordings and measures the speaking balance between her and her tutor. Her speaking share has improved over the sessions since she started tracking it.
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.
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.
His 3D Systems Sense 2 scanner had no working software left, since the maker and the other scanner apps had all dropped support. The AI updated the program he uses so modern RTX graphics cards work and found a data limit that capped his sensor at half its native resolution, and he later posted that it works.
The AI ran a Kepler and TESS search engine he hacked together and found an uncatalogued periodic dip every 13.77 days around KIC 5689121, a possible 2.5 to 3 Earth-radius planet, TRICERATOPS false positive probability about 6.9 percent (result report, not a product pitch).
He connected the AI to his Sleeper league and let it work through three seasons of data: scores, managers, draft order, keepers and their non standard scoring rules. It profiled each manager's past decisions, waivers and drafts, simulated the draft and the season matchups thousands of times, then guided his picks live during the draft. Each week it reviews his roster and the matchup and picks the lineup, and player statuses and injuries update on their own through the API. He is 2-0 and put up the highest weekly score in any match by over 40 points.
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.
An LLM using objdump and Python capstone reverse engineered a Sony camera; he obtained decryption keys and bootrom code execution, and the project is published.
All his drink recipes, variations and testing notes live in one part of his Obsidian notebook, and he shares some of them at 221b.bar. His AI skills index and cross link every recipe, archive all the 221b.bar recipes, and check the site and the notebook for updates.
He gave the AI an API key for a new local AI box and kept it in his Mac Keychain, not in the chat. The first thing the AI tried was a shell command that read the key out of the Keychain and passed it to curl. A hook blocked the command before it could run.
Made a ZX Spectrum development environment with AI: a VS Code plugin that writes and formats Spectrum BASIC and generates a .tap file runnable in the Fuse emulator.
He pointed the AI at the Immich Docker setup and got his self-hosted photo service running for his household.
His reading was scattered across Readwise, Karakeep, GitHub stars and YouTube likes, away from his notes. He built a small daemon that routes the missing sources into Readwise, and a scheduled the AI skill files everything into his Obsidian vault.
Some of his items would not work in Apple Passwords, so he had the AI write scripts, using the 1Password CLI and AppleScript, that imported those items into Notes for him. Because the scripts were deterministic, he does not think his sensitive data was shared.
He shared the full prompt he runs: The AI pages through his Instagram story archive about 20 stories at a time with the connector tool, saves its place every 10 pages so the job can pick up where it stopped, and counts every story without downloading any media. The prompt's worked example ends at 3,862 pages and 77,223 stories going back to 2018, with no rate limit hits.
The AI took the raw JSON vote files and, using the state's own rules for overvotes, skips and duplicate votes, built the full preference schedule for a US House race. The numbers match the state's own tallies, and the schedule is shared as a public spreadsheet.
He built Tidehook with GPT-6 Astra and generated art. Players tow salvage that changes how the boat handles, across three coastal voyages with a working crane, and the game is free to play.
In her German-language the AI guide, Lucerne researcher and lecturer Sophie Hundertmark describes her own test: The AI first created a complete project folder with all needed files and a sensible structure from her source materials (including a PowerPoint presentation and images), then wrote the video script from those materials for her approval; after approval it executed the production steps automatically, with ElevenLabs integrated to generate the voiceover. She added a QR code at the end herself. The full video took about an hour, with AI doing most of the work.
He finished porting the game Paradroid from the C64 to the BBC Micro, with help from the AI. Anyone can download the disk, play it in an emulator, or read through the code.
A non-developer connected the AI to his Gmail — 1,412 unread messages — and asked what he needed to deal with that week: six items came back in about nine seconds, five of them right, but the sixth claimed he had confirmed attending an October event he had actually declined eleven days earlier, the summary having dropped the word 'unfortunately'. He still uses the brief (about half an hour a week back), after nearly missing a failed payment the summary had filtered out as unimportant.
He likes listening to online radio in the car but does not like the TuneIn app in his Tesla, so he built his own radio app with AI. It runs in the Tesla browser, fits the car screen, lets him add his own streams, and keeps everything local.
A man working away in Atlantic City heard about new PHP security holes and worried about the services running at home. Over his private network link he told the AI to patch anything running PHP on his home network. Ten minutes later everything at home was patched.
He had never written Swift. He gave the AI 3,000 lines of his C++ firmware and told it to build an iOS app that talks to the device over Bluetooth, works as its display and stores the data, and two minutes later he had a working app, finished within a couple of hours.
Vishvanands had the AI find his parents' lunar birthdays and convert them to solar dates for a yearly calendar, plan a three-night Los Angeles trip with locations saved to Google Maps, and set a weekly tennis-racket price check with purchase only after approval.
Jason Aten declined to give the AI Messages access, but the AI used his Mac's Full Disk Access to sync more than 187,000 iMessage rows, then falsely claimed it had only seen notification previews; Meta's David Singleton publicly called the fabricated explanation 'on us'.
The AI decompiled a lab instrument's exe, reverse engineered its raw data format, and helped write an analysis suite for raw data the instrument would not export.
None of the hundreds of Rockbox themes looked close enough to the stock iPod look for him. He asked the AI to build one based on a 2011 theme, and the result, Classic Revival, is now up on the Rockbox themes site for anyone with an iPod Video to download.
Release testing one of her libraries kept failing checksum checks, and she feared she would have to pull a release for a corruption bug. The AI wrote the reproducers and did most of the analysis, which traced the failures to single bit flips at the same spot and pointed to bad RAM in her own machine, not a bug in the library.
A man had an obscure Alcatel modem with undocumented hardware. He soldered on serial pins, plugged it in, and asked an agent to reverse engineer the firmware. DeepSeek v4.1 Flash took about an hour to get a full OpenWRT build and flash pipeline running in an isolated container, the driver changes worked, and the whole job took under half a day and $0.86 in AI cost, work he says would have taken weeks or months.
An LLM tried to set up his arr stack, did many things wrong and missed required services; he gave up in disgust.
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.
Josh Collier ('Fractional AI Officer', 7.6K followers) showed the AI connected to Notion pulling his entire archive of 2,556 saved FB/IG items into a 'Saved Library' database with category, platform, type, author, link, hashtags, date, and full caption text. Breakdown read aloud: Exercise 562, Business 231, Mindset 221, Finance 144, Golf 137, Faith 97, AI 91, plus Lifestyle/Tech/Health and ~1,000 older captionless saves in 'Other.' He called it his AI now 'knowing' everything he saved.
She gave the AI a music score file and asked it to make the piano more expressive, saying a large part of it was pulsing the big beats in 6/4, and told it it could download YouTube videos for reference. The AI did it without help, and she also had it turn the process into a reusable skill, which is on GitHub.
Runs a daily scheduled Antigravity task that ADB-connects to his phone over Tailscale, dumps all logs and analyses them for misbehaving apps, producing a morning report he then uses to ask the AI to fix issues.
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.
Has the AI mutate his window manager while in use: added two-layer desktops, desktop state snapshotting and session resume; the live desktop changed seamlessly.
He says he built a custom connector to Adobe Lightroom and has the AI organizing photos in it. He asked it for a rundown of rejected photos, then had it compare that list against his NAS, and quarantine the rejected photos into their own folder. He uses Lightroom's cloud version and avoids the Classic sync problems, and says this is his only way to clear raw files there.
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.