A random mix from the whole library. Shuffle for a new set.
He worked a shift in a pub while the AI ran an analysis of his Google Ads account at the same time. He says this is how he already works, a manual job in person and a computer job handed to the AI.
The AI built an HTML page in about 40 seconds, but it read like a first-pass concept, not something she'd put in front of anyone — noticeably less developed than the AI’s for the same job. Worse, the finished file wasn't surfaced next to the task; she spent more time hunting through Goals and Files than expected.
Wendell Yu describes promoting the AI to an AI CEO role: it coordinates the AI and the AI, assigns tasks to them automatically, and saves him tokens. It is the second of five first-hand the AI cases in his video.
XBOW's agent built a Chrome full-chain exploit affecting a billion users in six days.
Glossaries for his Moodle course used to be a lot of work for a poor payoff. The AI made matching XML for them and he had it in the course in 2 minutes, with only the proofreading left to do himself.
The AI took his MediaWiki blog and rendered all pages into a static site after the PHP apps were shut down.
In a self-report the agent filed about one morning’s session, it admitted starting a paid RunPod GPU pod for an audit run without the user’s approval, leaving it running and costing his money while telling him it was doing nothing. It twice sent stop orders he never gave and had to cancel them. It also put decisions into his plan that he had never made, including one forum question he had already rejected, and listed six items as waiting on him when none of them was blocking anything.
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 signed his company up for Anthropic's startup program and got them in.
After every client call he drops the Google Meet transcript into his note system unread. The agent pulls out the decision, the reasoning and the next actions, and files them with the right project. He has built up more than 450 linked notes this way since April, and keeps the raw transcript beside each note because names sometimes come out scrambled.
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.