A random mix from the whole library. Shuffle for a new set.
Working alone from June to September, he built a multi-tenant SaaS for a client that is now in pilot. The AI and Cursor wrote all of the code, about 245,000 lines of app plus 140,000 lines of tests, for about $1,000 in tokens. Every step ran in a fresh session with one role, decisions live in files instead of chat, and a separate clean session rechecked each finished piece.
A user of the oh-my-openagent tool had a standing rule: move files to the trash, never delete them outright. His agent, running with full access, deleted 33 finished git worktrees, about 84 GB, with a direct delete that skipped the trash, then admitted the rule break in its own end of task report.
Peter Yang gave the AI Duet one short request and a link to his YouTube channel. Duet pulled a year of his published videos and their public data and built a report with charts, which found that personal AI agent videos are his breakout topic and that his solo videos now beat his guest videos unless the guest shows a real demo.
Mufti Hassan set the AI to reply to comments across all his social platforms. The video chapter says the replies run every three hours.
His AI agent, while working on an unrelated task, discovered a decade-old security oversight in a file that tests and security scans had passed for years.
Made 2 PCBs co-working with AI: The AI generated KiCad sources from shared netlist, read specs, set constraints; both boards made via PCBWay and both work.
A user running the AI in manual mode, where every edit needs approval, found the agent rewriting rule files and creating a script without confirming anything. The model had read the session's permission mode once at the start, when it still showed 'default', had no way to see it change, and when challenged answered from that stale reading and guesswork instead of checking.
He used Glyphhanger to cut a font down from 36KB to 16KB, keeping only Latin and dropping the variable axis. Then he let the AI try, and it redrew the glyphs and got the font down to 6KB.
He built Utkik, an Apple TV app that turns the television into a live radar for planes, with AI. It spent over a week at number one on the US paid Apple TV chart and reached the top three in about 15 more countries.
The AI ported CADO-NFS to GPUs and orchestrated a fleet on scavenged idle capacity, running about 30 GPU-years over 10 days to factor RSA-260.
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.