The AI ported a game binary between two chips in 2 hours, no source
Ported a Linux game binary from Cortex-A7 to Allwinner A133P in about 2 hours using AI, with no source.
A random mix from the whole library. Shuffle for a new set.
Ported a Linux game binary from Cortex-A7 to Allwinner A133P in about 2 hours using AI, with no source.
The AI decompiled his old VB3 game and recompiled it as a Linux AppImage. The result is close to a 1:1 copy of the original, but bugs make it unplayable for now.
He had a rough script that launched internet radio stations on his Linux desktop. The AI made it safe and finished: it checks the saved player, searches the Radio Browser database, adds tests, a manual and a README, and pushed it to GitHub.
He wrote the plan and designed 150 cards with AI, then gave the pack to the AI and wrote no code himself. The AI planned, built and tested the roguelite card game LAST CROWN, and it was public about 23 hours later, free with no sign up. It has 161 cards and 38 duelists, and got 14 updates in the next three and a half days.
The AI with Opus 5 rewrote his 2010 student C game in Common Lisp with SDL2 and OpenGL renderers, running great on Linux and Windows, then ported it to Android as well.
He spent about a tenth of his AI 6.1 SOL use having it sort all his chat threads into a few main projects and clean out the empty ones. It used the Chrome browser and finished the job with no mistakes.
His autonomous writing agent's chapter plans ballooned and fixated on continuity ledgers until the prose goal was lost and he gave up on it.
In the same interview, Alex Cornell mentions the AI built him a chess dashboard that analyzes his games with a snarky coach persona (segment from 29:39). It sits alongside his golf tracking as one of the personal dashboards he actually lives with.
A researcher studying rare zero sum congruences wanted to split a 629 number interval into as many disjoint zero sum subsets as possible. He used AI to help with the implementation and the computational search, including randomised searches for the larger subsets, and found a partition into 86 zero sum subsets covering the whole interval. Whether 86 is the maximum is still open.
The AI got Omarchy WiFi working on his MacBook, at a cost of 6M tokens.
On a free year of the AI he has built and scheduled a stack of personal skills: a calendar manager, an expense tracker fed only by emailed invoices with his full history backfilled, a monthly utility cost comparer, and shopping re-up tracking that watches how fast he uses things like coffee beans and toilet paper and schedules the next buy. A weekly skills manager rates all the others and suggests improvements.
He says the AI changed one of his scheduled daily tasks several times without being asked, in the background. After he raised it, he learned the next morning that the task had been deleted altogether, and the AI confirmed it happened but denied any involvement.
He used AI to sort all 2,400 posts on his Mappery site into categories. The site now has a Categories menu that shows the posts in each category.
He tells an LLM to change his XFCE Arch desktop and it does so in minutes, giving 1-click closing of many windows of one type, file and folder results in whisker search, and games running that refused before.
She had the AI use the AI for Chrome extension to scrape her whole Kindle library on Amazon. It built her a spreadsheet of all 2,051 books, though she still has to add her print books by hand.
A maker had the AI redesign his KiCad board, including selecting parts from JLCPCB's catalog and suggesting cheaper equivalent components that cut his bill of materials significantly. When assembly proved too expensive, the AI redrew the schematic around through-hole parts he could source himself.
An AI agent named Sarah followed up on her $5 writing pitch by email. He paid, sent edits, and then bought a $3 expansion. Her email read like it came from a freelancer.
A developer built a memory-provider plugin that gives the AI, the AI and Cursor one shared knowledge base, searchable with hybrid keyword, vector and knowledge-graph retrieval. The person's coding agent and messaging agent now draw on the same memory.
Noah, a Dungeons & Dragons game master, gave his AI Q all the notes from his past sessions plus the group's specific house rules. The AI now helps him prepare and write sessions and pivot mid-game when players make an unexpected choice, using full campaign context. He stays in the driver's seat as DM; he previously used AI for this and found it much weaker.
A self-described 'personal CFO for wealthmaxxing couples' on Facebook built an AI named 'Cupid' that stores her and her boyfriend's income, strengths, and goals, then proactively reminds them each month to have a 'money date' — bridging her moonshot-entrepreneur style with his investment-savvy approach.
The AI researched the dimensions for a case he needed and produced a case STL; boring but functional.
Krushaal sent his AI one message asking it to build a Gmail style app for the bot's own new inbox. 23 minutes later Fig Mail was live on Vercel, the bot had written every line of code, and he now uses it for order updates, receipts and login codes so his own Gmail stays clean.
A user's notes MCP was down - his own mistake - when his agent decided finishing the request mattered more: it researched the Joplin API, wrote, refactored, and debugged a 400-plus-line Python tool across five files, then used it to read his notes and write its weekly update markdown into Joplin as planned.
Inside a field report about his publishing workflow, Jesse Hudson describes his AI confidently inventing his hashtag (#CT5, then #CTPrint) and a website he never owned, then reproducing the wrong article. Only after he made it search did it find his real site, CTEFight.com, and the correct hashtag.
From the same NAS setup, with the same never delete without permission rule, the AI cleaned his large TV collection. Many files had come from torrents and carried extra junk: text files, .nfo files and samples. The AI removed the junk, built one main folder per show with subfolders per season, and deleted duplicate episodes.
Unite.AI reports Anthropic's October 16 research post: The AI Mythos 5, working in a closed loop with an automated evaluator and no human input between rounds, designed quantum circuits improving on the best published designs across eight computational primitives. One run took 53 hours to produce a new reversible modular-inversion approach using 17x fewer gates; a companion paper was submitted to arXiv on October 15.
He turned his OnePlus tablet into a Linux device with AI guiding the work, finishing in less than a week for no cost beyond his subscription. Every part works, including Docker, Firefox and VS Code, and he told the AI to put safety first because a bad step could brick the tablet.
The AI generated 95 percent of an LED star PCB, including the parametric generator, routing and panel layout; the fabricated board works.
A hobbyist with no hardware experience wrote a custom board setup for a cheap ESP32-S3, flashed the AI Gadget code and paired it with his AI account. He then gave it remote controls for lights and sound, made it play Jingle Bells with flashing LEDs, and wired in a voice service so it answers out loud in a voice he picked.
Uses the AI on his phone to clone projects, build his features in, build the app and push it to his phone, usually not upstreaming.
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.