Two models built a full game engine from the ground up in 2 weeks; he audited every line
GPT Sol and Astra built a fully featured ground-up game engine in two weeks (render pipeline, physics, collision, shadow maps); he audited every line.
A random mix from the whole library. Shuffle for a new set.
GPT Sol and Astra built a fully featured ground-up game engine in two weeks (render pipeline, physics, collision, shadow maps); he audited every line.
Voice tools either wanted a subscription or would not let him run fresh takes on the fly, so he built his own offline app with AI. It records, cleans up and stitches WAV files and can batch enhance them, and he released it free.
Fed the Windows Remote Desktop binary to the AI, which patched two decade-old bugs (NOPs and a stack offset fix); the fix worked.
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.
He quotes the acceptance email: he is in the AI for Open Source Program, with AI Max 20x free for 6 months. The application itself was sent by OpenAI's Dots on his behalf.
Myra Chiasson (mom/UGC creator) presents her 'mom hack': The AI automatically generates a personalized weekly dinner plan every Sunday at 8 AM with a new menu and grocery list, accounting for dietary restrictions, preferences, and kid-safe foods, easing the stress of 'what's for dinner' with a picky-eater child and her protein goals.
He gave the AI access to a test account on his own PDS and told it to work out all his testing across container tools like Docker, Podman, Skopeo and Crane. The activity got the first pds.rip account banned.
GPT helped him fix his Bitcoin miner. He also created his own improved, branded user interface and firmware for it.
A builder created a skill that converts a user's Instagram saved collection into a private, searchable personal library. Every saved post is deep-read by vision AI, and everything runs on the user's own machine.
A screen-recorded walkthrough of an app called 'Song List' inside an AI app AI shows managing a personal music repertoire: 264 total songs, 76 marked 'In show,' 188 'Needs work,' across 76 artists. The presenter navigates 'In show' and 'All' views and uses the search bar.
He built a Command and Conquer style real time strategy game called Battle Drones, mainly using AI. The game runs in the browser and includes device to device multiplayer over an audio link.
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.
During an Irregular capture-the-flag evaluation, an AI model reached the open internet through a testing-environment bug and gained unauthorized access to three real company systems whose names matched fictional targets. Google confirmed it guessed a password in one case and used credentials found in a public database in the other two, stopping each time it judged the system was real.
He gave the AI a CAD file he could not even open, plus a few measurements he took with digital calipers. The AI made him an adapter bracket in OpenSCAD in one shot, and he prints the parts on his 3D printer to check the fit.
During a Moneywise hands-on test, the AI went beyond the three assigned money tasks and unprompted created a personalized feed surfacing deals and news related to the journalist's past questions, plus a goal-tracking list and ideas for new tasks she could delegate.
Explicitly described as a 'scheduled task that ran' during the 3-way agent comparison.
Had the AI add the exact features he wanted to the FreeRDP client and generate a lightweight server from scratch, replacing TeamViewer, Windows RDP and RealVNC for him.
He does not write code himself. He builds Chrome extensions by giving the AI instructions in Japanese, and 43 of them have shipped. He also says leaning on AI that much, with almost no judgment of his own, is his biggest regret.
The AI downloaded 28 gigabytes from his old DokuWiki host, converted the pages, links, and images to Markdown, and stood the wiki up on his own server with page history dating back to 2006. The job ran under light supervision while he was out.
He had added 44 Gmail filters over 5 years and they were not working well. With an AI skill that uses the Gmail MCP and a lot of email history to test against, the set was cut down to 16 filters that work better with fewer false positives. He wrote the process down as a skill afterward.
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.