He had the AI download every video still left on a Twitch streamer’s channel, since Twitch only keeps archives about three months. The AI ran OpenAI speech-to-text twice for about $80, then made an HTML page summing up the public background the streamer had mentioned on stream.
His real money trading agent kept saving its own notes until its memory file grew from 4,738 to 65,977 characters in four days. One night it retried a failing step 51 times, burned $36.91, and ate 43% of his whole project API spend.
This one went wrong. See what happened before you try it.
Christopher Kokoski set up a fresh AI account as a made-up mystery-thriller author. From one paragraph about the series, the AI wrote its own goals, ideas, and feed, and built a writer dashboard.
A father's son grew his hair since Covid and cut it to donate to a charity that makes wigs for children with cancer. The father kept putting off making a poster, then gave the AI a couple of photos and a video link and it built the poster while he worked. His boss put it up, workmates pledged enough to fund the wig, 250 pounds. Later, from the car, he voice prompted the AI to remake the poster in his son's words for the boy's school, and forwarded it on WhatsApp when they arrived.
Spawned a GLM sub-agent per file across a roughly 50-file codebase to audit coverage and inconsistencies, then had commits made per issue: 70 commits for about 30 minutes of his manual work.
Fulton's the AI flagged an Economist interview with Andrew Ng that matched his interests, wrote him a primer before it started, and placed it on both his personal and work calendars. He had not asked it to connect those dots.
In a hands-on test on a $20-a-month Google AI Pro account, the AI renamed and organised a folder of 507 PDFs into 13 subfolders. The session drew a broad warning that granting folder access could include sharing the folder's contents with third parties, plus a notice that backups of connected files would be deleted after a follow-up or 24 hours.
John Voorhees has his Dot, Puck, coordinate his work: he spins large projects off into AI threads and lets the Dot manage them, alongside setting up tasks, checking email and doing light research. He says the delegation has worked reliably the couple of times he has used it.