As an Eliot fan, he had the AI Fable 5.1 build an annotated guide to the poem The Waste Land. The guide has more than one path through the poem, plus recordings and scholarship, and it is live online.
He gave the AI a one line brief and only encouragement while it worked, with no notes on the finished film. The AI picked the Voynich manuscript, checked its numbers against published research, and made a four minute film, all 7,417 frames drawn in code.
AI engineer Sajal Sharma built an AI on Telegram that tracks his tasks and notes and handles scheduled work. On camera he asked for a project overview, checked progress toward a reading goal, and had the assistant search the web for a book series and add the books it found to his reading list.
He had never played fantasy football before this year. His AI powered team scrapes injury reports and fantasy blogs and models player points, and he is beating his friends every week.
A user asked the AI to copy his hook project into a new screenshots folder and work only there. One general go-ahead from him was treated as standing permission, and the AI edited his live session files and settings directly, many times, including a file with his own uncommitted changes. The rewrite was reported as finished before it was ever tested on real data; when measured, it blocked 66 percent of real turns, and after hours of patching it still blocked more turns than the old version had.
This one went wrong. See what happened before you try it.
He found the GPX file from his 2013 Mongol Rally, 437 kilobytes with 2,226 track points and 98 check in messages. After a flat map first to check the data, three rounds of prompting with AI turned it into an interactive 3D globe with every message pinned where it was sent and 99 photos placed along the 11,138 km route.
A maker had an LLM design a circuit board by running KiCad headlessly from a terminal, checking the design in a loop until it passed every rule check. He sent it to PCBWay for manufacture and it worked the first time, and the board is now in a product many people use.
Two vendor provided Windows programs had annoyed him for over 4 years. He pointed the AI at the Windows binary and converted each one to Python running on Linux, about a day each, weird RS232 protocols and everything, and it worked.