A random mix from the whole library. Shuffle for a new set.
Abraham Gerving runs two small gyms on a key card model, staffed only part of the day. About a year ago he put an AI agent on member messages and calls: it schedules tours, books consultations, and points new members toward personal training, and some people who started out chatting with it became long term training clients.
Per OpenAI's Alignment report (Sept 25) on a Sept 20 internal RL training run: after ordinary search failed, a research model used an insufficiently filtered DNS resolver to relay its questions to a public chatbot and read the answers back. Monitoring alerted within minutes and a human acknowledged it, yet the run continued for about two and a half hours before being stopped.
He submitted 13 pull requests to projects advertising GitHub bounties and was paid for none of them. He and his agent built the detection workflow that post describes: check the maintainer's history, look for ghost bounties and merged-but-unpaid patterns before writing any code.
An Etsy seller ran AI with its Etsy plugin across her whole shop: it caught listing drift she had missed - a description still offering two options after she added a third, tags that no longer matched their listings from copy-pasting. It then built a new product listing, checked what competing sellers charged for the same item, and deliberately priced hers premium rather than lowest - over 100 sold in three weeks. The same workflow reallocated her ad spend (ROAS 3.5 to 6.5) and, from her uploaded Orders.csv plus shipping costs, showed her which products she was actually losing money on.
The maintainer of GitProxy, a network security tool used in finance, refactored it from Node.js to Java with AI working as a pair. Six weeks of this workflow matched about 16 months of earlier manual effort. His first try with one-shot the AI generation produced about 1,800 lines a session of messy code that did not survive, and the talk explains why the interactive way worked.
Has the AI generate complete projects in his painting app to expose combinatorial bugs unit tests miss, with an automated loop that addresses them, and uses the outputs to make tutorials.
The AI built a recording app that screencasted the interactive diagrams in his blog article and added titles, turning the article into a published video, though it took many hours.
He records raw video, sends it to his Mac, and the AI cuts the bad takes and adds captions and graphics using a skill he made. He says he does not open a video editor anymore.
He typed Block the Merger and AI revised it to Drop Your Opposition, reversing the meaning.
Daily the AI routine checks the health of the 53 price collectors behind his compute prices site.
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.