An LLM tuned his voxel game from 12 frames a second to 60 over 3 days
An LLM performance-tuned his Godot voxel game over 3 days, taking it from 12 fps to 60 fps with diagnostics and render changes.
A random mix from the whole library. Shuffle for a new set.
An LLM performance-tuned his Godot voxel game over 3 days, taking it from 12 fps to 60 fps with diagnostics and render changes.
He had the AI reverse engineer a PlayStation 2 game he had the bytes for. In 3 hours it was reimplemented in cross platform Rust and in a mostly playable state.
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.
Set the AI on it for a few hours and got Office 365 working under Wine on Linux, published as a working flake he uses with his own account.
A researcher updating his own old question says he now asks his agent to download the papers his reference manager could not get. The agent works in the browser while he is signed in with his school login, and he clicks through the human checks himself.
The AI rewrote the touchpad stack on his ThinkPad T14 running Linux and Hyprland. Touch to cursor time went from about 33 ms to about 18 ms.
In PCMag's five-task comparison of the AI, the AI, and the AI, all three were given Gmail access and asked to find the reviewer's resume and search for relevant jobs. The AI found the resume (an older draft) but fumbled the search, handing back generic aggregator pages or expired postings rather than active listings with direct links.
A man set up his agent setup so the AI could ping him on Telegram when it needed hands. Working on hardware together, he got a message every 5 to 15 minutes telling him to move a resistor or patch cable in a set way, and following the instructions they got the hardware working the way he wanted.
Fed the Windows Remote Desktop binary to the AI, which patched two decade-old bugs (NOPs and a stack offset fix); the fix worked.
He drafts in an AI app, and the AI itself sorts each piece, tags it, and moves it word for word into his Obsidian vault using a skill he built. The filing runs as part of how he writes.
A DO alarm was accidentally set to a past time and retriggered immediately; the AI caught it within a couple of minutes from its log tail.
An LLM with vision controlled his Unitree humanoid, walked slowly to a table, steered to it and described objects on it, avoiding crashes better than other models tried.
The AI worked through data-broker removal requests for the user and got four broker listings about them suppressed.
Opus finished a first PCB that had sat at 90 percent done for 6 months.
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.
Runs a personal-assistant session via Signal that tracks tasks and delegates to per-project agent sessions on other machines; it is now his only direct interface.
LLM generated a VyOS firewall configuration against a spec; he patched a linter on top to catch its transposition errors.
His agents lived on his desktop, so he had to walk back to the computer to read what they left him. When APX got an Android app, he did not install it himself. He asked Roby, and it pulled the ADB skill and installed the app over USB.
He left Twitter in 2022 and had wanted his archive in the Day One journal app ever since. The AI did the import in an hour, and that time included backing up his databases first in case anything went wrong.
Built about a dozen boards using GPT-5.6 Sol; his favourite is a Pi CM5 carrier board replacing the laptop board in an old Sony Vaio P.
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.