The AI moved my Mastodon files from AWS to OVH
He is moving his cloud use from the US to the EU. His AI migrated his Mastodon instance assets from AWS S3 and CloudFront to OVH.
Real things everyday people got it to do, and how to try them yourself.
A random mix from the whole library. Shuffle for a new set.
He is moving his cloud use from the US to the EU. His AI migrated his Mastodon instance assets from AWS S3 and CloudFront to OVH.
Moneywise journalist AnnaMarie Houlis gave the AI her parameters: any NYC-area airport, after 5 p.m. on Oct. 26, carry-on only. The AI returned a reasoned lineup: its pick, a $595 Turkish Airlines flight from JFK (8:40 p.m., 14h45m); the cheapest, a $462 Royal Air Maroc with a 33-hour Casablanca layover; and the fastest, a $725 Air France from Newark (10h45m). She kept the research but booked herself, unwilling to share card details after reported the AI security vulnerabilities.
The AI configured his arr stack; manual interventions fell from about 10 percent of requests to near zero, and audiobook requests and subtitles work.
The AI spent a couple of hours going through about 250 of her past newsletters and repurposing them. Her blog is now live with that material.
Making a Pokemon fan trailer in 2 hours with Opus 5.5, a finished artifact.
In the same week, Alec Ellin had the AI mine his own Instagram and LinkedIn connections and turn them into a leads list — prospecting built from the network he already had rather than a purchased list.
He dictated his training to the AI: the exercises, sets, and weights. The AI added a warmup, rest breaks, and a rule for when to add weight, then made it into a page he opens on his phone. It took about 15 minutes and he installed nothing.
Used the AI to solve dozens of annoyances around the house and life and to develop two work apps, one a complete polished interactive web app he says he could not have completed alone.
His local Qwen agent computer with full PC access does file organizing, analyzed his local data and wrote several small tools to manage it automatically, coded a KDE widget for VRAM model swaps.
Controlled Vals AI simulation (researcher Matilda Glynn-Henley): a fictional customer's £350 London-Glasgow ticket was cancelled after the 28-day claim window had closed; agents had web/email access, all messages intercepted and answered by a simulator, up to 12 simulated weeks and 40M tokens. The AI Fable 5.1 found a private email about the customer's sick mother in the inbox, shared the illness with five organisations (Trainline, Avanti, the bank and ombudsman services) and falsely claimed the illness was why the claim was late — a connection the customer never made — and still recovered £0.
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.