He wrote the plan and designed 150 cards with AI, then gave the pack to the AI and wrote no code himself. The AI planned, built and tested the roguelite card game LAST CROWN, and it was public about 23 hours later, free with no sign up. It has 161 cards and 38 duelists, and got 14 updates in the next three and a half days.
A user asked the AI to archive the files it could see and send them to his Google Drive. The AI sent an archive of about 6.8 GB unpacked, including its own internal documentation, agent logs and SSH key files, and he reported it through Meta's bug bounty program.
This one went wrong. See what happened before you try it.
Author Matt Deitke fed an entire book to the AI and had it generate a chapter-by-chapter podcast website, with subagents handling chapters in parallel. The output was a finished multi-episode podcast series derived from the book.
Claroc researchers ran one passive-DNS search on the AI’s content domain and enumerated more than 6,800 share pages, because each share's web address is built from its conversation title plus its random ID. Among a few hundred opened pages were a small-business loan application, a CEO revenue review, a bank fraud alert with a partial account number, and confidential executive-search call prep; Meta suspended the sharing feature on October 20 after Ars Technica asked about the findings.
This one went wrong. See what happened before you try it.
The AI interpreted scanned old service manuals and circuit diagrams, ran simulation experiments to verify manual claims, cross-checked datasheets and papers, caught typos and his own misreadings.
His talk archive site had been a work in progress for years. He asked the AI to help track down records of talks he has given, and the site now contains 115 presentations covering 26 years.
He runs AI on his own server with Ollama, so it stays private. It keeps his to-dos in a simple text file, sends him reminders about upcoming due dates, and takes new tasks through Telegram chat or voice.
She wrote an AI script that transcribes her French tutoring recordings and measures the speaking balance between her and her tutor. Her speaking share has improved over the sessions since she started tracking it.
Gail Moody (1.8K followers) ran a head-to-head trial of two AI assistants. For finding parking in San Francisco, she says the AI gave 'lame ass suggestions' and couldn't complete the transaction, while Instinct booked a SpotHero space at Plaza Parking with just her approval.
This one went wrong. See what happened before you try it.
His YouTube videos kept jumping back 20 seconds when a tab reloaded, so he connected GPT to his Chrome browser through the DevTools MCP and let it run tests and read the site code. It found the checkpoint time comes from YouTube's server already 20 seconds early, and he opened a bug report to YouTube with what he found.
AWS opened the AI Business Strategist beta exam on September 29, 2026 with no third party study material. He built an AI project connected to Notion, loaded the exam guide and course material, and used AI drills, practice tests and a fact sheet to study. He sat the exam on its first day and passed.
He scraped a friend's two social media profiles, made a plan, and had the AI create a website for them. In about half an hour he had a site to show them.
His role was eliminated on Tuesday morning. That evening he asked the AI for something fun, and by 9 PM there was a 3 stage 16 bit co-op game where the hiring process is the final boss. By 6:37 the next morning it was live on the internet, with 38 commits and 325 tests in a public repo.
Ahmad Alkabra posted on X that he tried an insurance prompt sourced from an AI use-case account and received safety and scope warnings, including that the AI would not pose as a licensed insurance broker. No quote, policy change, or saving was reported — the task was refused on licensing grounds.
This one went wrong. See what happened before you try it.
After giving someone a book they already had, he used AI CLI to build a small app for gift ideas. It suggests gifts from his own 5 star book reviews and the other person's Goodreads wishlist.
He ran his apps on a Raspberry Pi and paid for a VPS to keep the AI away from live operations. The AI worked out the spec for a PC that could run two virtual machines, researched eBay and found a good deal, and he followed its instructions, mostly by pasting commands on his phone, to set up both machines and move everything over.
A home-lab operator gave his AI access to a tools VM that runs nmap scans, then had the AI push the discovered devices, IPs, VLANs and virtualization components into Netbox through its API. He reports it running for a couple of weeks with no downsides so far while he keeps Netbox as his source of truth.