A random mix from the whole library. Shuffle for a new set.
Dheeraj Sharma built an AI cleanup agent for decade-old Gmail inboxes like a reader's 130,000-message one, then ran it on his own 7,610-message mailbox in four gated stages: census, editable plan, dry run, apply. One approved run moved 2,896 newsletter and notification emails to Trash in 107 seconds (unread fell from 5,013 to 2,237), with deletion impossible by design and every change logged for a one-command undo.
A researcher runs a coaching-history project under two written skills he authored for exactly this work. In one day the AI skipped the documented archive re-login procedure and used a generic browser restart instead, a repeat of a mistake already corrected before. It put an unverified coach ID, 209 instead of the real 294, into drafted research notes before checking the production database. And it ran a site-wide newspaper archive search where the written technique required scoping to three named papers. Every error was against a procedure that already existed in writing.
He gave the AI one big job: go through his entire Zotero library and build an Obsidian vault on disk that documents every article, sums each one up, pulls out the key ideas and links articles that share ideas. It ran for 34 hours straight on his 20 euro the AI plan without hitting a limit.
Over a few days he used an LLM to create a complete court document bundle for a Judicial Review at the Manchester High Court. He filed the documents today and the court issued them within 5.5 hours, something he says he had no chance of doing on his own.
An LLM crunched for 36 hours on a project he had wanted for 5 years; checked and ready to deploy, work he estimates would have taken him about 9 months.
He asked the AI to check a document against his checklist. The AI built a color coded system to rank the issues, added colored comments to the document, and finished in 10 minutes, work he says would have cost him 3 hours.
The AI restyled a survival plot for a cancer journal but put the results table over the data. He explained what was wrong, had the AI write the corrections into a skill file, and those corrections are now the default.
A Japanese Threads creator split his account's operation into six AI agents with one deliverable each (researcher, writer, poster, fetcher, analyst, supervisor) and reports 1,181+ posts and over 10 million cumulative impressions. The writer agent may only cite numbers stored in a single 'truth file' so it cannot inflate results, the poster must confirm the published URL rather than the button click, and the fetcher records 'not retrieved' instead of zero when a fetch fails.
The AI wrote Zig tools in real use, including a wasm utility integrated into a site and reverse engineering a USB wire protocol for an industrial camera driver.
His agent runs once a week: it finds companies on Google Maps, finds a real person's contact details on the web, and drafts a personal email for each one, which he approves before it sends. Across 200 companies it produced 20 interviews in four weeks, and he spends about an hour a day on the replies.
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.