An agent checks his lecturer partner's references against the real sources
Built an LLM-backed reference checker for his partner, a lecturer: an agent reads each cited source and checks the reference is correct and not hallucinated.
A random mix from the whole library. Shuffle for a new set.
Built an LLM-backed reference checker for his partner, a lecturer: an agent reads each cited source and checks the reference is correct and not hallucinated.
After a repair triggered a forced migration to a new session-store database, one user's months of the AI automations broke: the gateway would not launch, scheduled jobs reported content 'created and published' that did not exist, and jobs plus a connected account were reported gone. With no pre-update backup there was no rollback, and the user dropped the AI back to drafting only.
After putting it off for years, he worked with AI over a few sessions to build a homepage for his genealogy research. The page is up with links to eight parts of his work, and three of them already have material on them.
Over two weeks the AI built his hobby tool that matches free Sentinel-1 radar images with live AIS ship data around Denmark, recording AIS either side of each satellite pass on its own and marking radar spots with no ship as leads. In one check 2 to 5 of about 555 pairings were wrong.
Student has the AI review generated code on side projects; it caught a real security issue once.
Broke copy protection with GPT 5.6 and has a forked Hatari that boots and runs Notator and Creator by emulating the dongle.
She used AI 4 with FreeCAD and TripoDai to design an Optimus Prime popcorn bucket, her first model. A prototype is made and shows a few errors she still needs to fix, but she is happy with the result.
Uses an AI-implemented forced-alignment technique to generate sync files for epub and audiobooks, aligning a 60 hour book in 20 minutes on his GPU.
He asks the AI Agent to caption a video in Palmier Pro the same way as the previous one, and it does it from what it remembers. If there is no voice transcript, it writes code to make the captions happen.
The AI helped clean up his dotfiles and add automation and tests, used to switch devices and identities.
He directed the AI through shooting and editing a full music video for his DJ set. He said it cost nothing and he would use AI for video work again.
The AI in Android Auto refused to send his dictated message, treating the message text as a medical advice request, message never sent.
A creator who fixes AI-generated images in ComfyUI had the AI build him a full desktop editor, Scumble, over five weeks starting September 4: 632 commits and about 83,000 lines of app code, tested against his own pictures. It reached 43 releases and a Microsoft Store listing, and every feature doubles as a command an agent can call.
The AI used an adb and profiling harness to take the Eden emulator on a Pixel 10 from crashing to 2 fps to 20-30 fps in Breath of the Wild.
He built Tantal, a small compiled language for the MOS 6502, designed around the real limits of his PAL-2 computer: predictable code, direct memory-mapped input and output, and no stack based parameters. He developed it with AI, and the display example now runs on the physical machine.
He takes notes on both a Boox and a Samsung device and the two formats did not mix. He built an Android app with AI that converts both formats back and forth, so he can move his notes between them.
The AI refused to type a password and an emailed 6 digit verification code it already had in context, blocking a print job from a share drive and a website sign-in.
He asked the AI to move a long the AI conversation into a coding project. The AI picked a Safari extension he had written himself, recovered 1,651 messages and 97 artifacts, and checked the files.
AI engineer Sajal Sharma built an AI on Telegram that tracks his tasks and notes and handles scheduled work. On camera he asked for a project overview, checked progress toward a reading goal, and had the assistant search the web for a book series and add the books it found to his reading list.
Since the end of August he has added three new CI servers to his own setup. The AI wrote each NixOS setup and he checked the work, so now he can rebuild any of the servers from scratch in minutes.
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.