The AI checked 163 co-author profiles for me and found no Mastodon links
He asked the AI to check a researcher's co-authors on ORCID for possible Mastodon links. The AI checked 163 co-authors, 120 of whom had ORCID profiles, and found none.
A random mix from the whole library. Shuffle for a new set.
Work
Jobs, side gigs and small business · 1,695 ideasThe AI proved his formally specified code correct and found a few real bugs on the way
The AI proved his Verus and Rust code satisfied a carefully built spec and uncovered a few interesting bugs.
The AI chose 30 of my trip photos and put them in Notion
He gave the AI several hundred photos and told it to add photos to his Notion travel record page. It picked about 30, added them, and also made a route map from his GPX data.
My agent fixed my signup tracking. The new subscribers were bots.
Five new newsletter subscribers in three days were credited to direct traffic, so he asked the AI to inspect his PostHog analytics, his main site, and his newsletter site. It traced where the tracking was lost, changed the links, deployed and tested the fix, then checked the server logs and showed the signups were bots.
Run a marketing operation on 8 scheduled the AI tasks — and test the cloud move before it is forced
Charles Summers runs his demand-generation work on the AI: 8 scheduled tasks that drive HubSpot, Search Console, Gmail and LinkedIn through Chrome, backed by 578 local sessions and about 220 memory notes. Ahead of Anthropic's October 6 cloud switch he audited every task, backed up 7.9 GB of sessions, and ran a 14-point cloud readiness test — 13 passed, including a live HubSpot API call, and the one 'failure' was Cowork asking before deleting a file, as designed.
An agent ran 12 to 48 hours unattended on his plan and built large projects, a game included
Fable ran 12 to 48 hours largely unattended on his plan and test harness and built large projects, including a video game he wanted to play.
This only partly worked. Worth knowing before you try it.
The AI’s test scheduler cut his release builds from a minute to about 3 seconds
The AI wrote a test run scheduler and migrated to nextest, cutting local release build cycles from 60+ seconds to about 3 seconds.
His small businesses run on separate AI agents for inbox, outreach and quotes, and nothing goes out without his phone approval
He runs his own small businesses with AI agents. Each job has its own agent with its own instructions file: one triages the inbox, one handles outreach, one prepares quotes. The agents only draft; he approves every email and quote from his phone before it goes out. A brief arrives at a fixed time every morning with the overnight replies, what is waiting on him, and the follow-ups for the day, and it replaced his own daily check-in. When he corrects something, the correction goes into a shared notes file that every agent reads, so he only has to say it once.
An LLM built the sandbox a big project had left undone for almost a decade
An LLM built Homebrew's Landlock Linux sandbox that had sat unfixed on the roadmap for almost a decade, reviewed line by line by maintainers and shipped.
The AI ran the initial setup of a Facebook/Instagram ad campaign
Nari Media's test shows the AI making the initial setup of Facebook and Instagram ad campaigns fast and accessible for media buyers, handling the first build inside Meta's ad tools.
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.