The AI and the AI rebuilt his Tesla data tool in Go; five months of use says it works
The AI and the AI re-created a Tesla data tool in Go from an existing codebase at his request; he has used the new tool for 5 months and it works well.
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.
The AI and the AI re-created a Tesla data tool in Go from an existing codebase at his request; he has used the new tool for 5 months and it works well.
A refund of several hundred dollars was still pending, so Cramatata casually asked the AI to call Apple customer service and ask about its progress. The AI made the call, spoke with a live representative who checked the order and its progress item by item, and only transferred the call to her when identity verification was required.
The open-source 'burner' project gives the AI a real spare Android phone (Android 11+). The agent uses the phone's apps exactly like a human would — opening them, tapping, typing, scrolling — and sends the user screenshots, extending its reach to marketplaces and shopping apps with no website or API.
Over a few days he used AI models to rebuild a music visualizer he first made years ago, this time as a driving game live at youtubedrive.com. You paste a YouTube link, the song is pulled in, and the world moves to the music.
WIRED's Reece Rogers had the AI order breakfast from a bakery; the agent built the order correctly but quietly selected 'no tip.' Rogers ended up ordering in person — a small social-judgment failure that shows why checkout details need a human read before approval.
Luna finished an ESP32 SIP client for an in-wall touch panel that rings when someone is at his doorbell and lets him answer calls and see video.
The same man's system pulls every train, flight, hotel and ferry booking out of his email into one travel database. The AI answers his trip questions from it, sends his e-tickets to WhatsApp on the morning of travel, and messages him when there are delays. He averages about 300 pounds a month in delay claims and plans to have it file those next.
His team could not redact multilingual GDPR data from firewall logs fast enough by hand. He had the AI fine-tune a MiniLM model with EuroLLM as the teacher, and after two days of work and about 50 euros of GPU time the results were fantastic.
Engadget reporter Karissa Bell asked the AI to help research a potential multi-city international trip later in the year, giving it timing and a nonstop-flights-only preference. The AI returned flight options from her city, set up a price tracker to monitor costs at regular intervals, suggested how to order the route, and recommended considering a multi-city ticket so she could depart from a different airport than she flew into.
His team pushed devops workflow into agent skills and shut down when they hit a usage cap; the scripts turned out buggy and poorly documented, and the harnesses had been burning tokens muddling through instead of raising alerts.
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.