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.
Holdy logged the AI into his medical provider's portal and had it pull his itemized bills and question every line. It found several cases of double billing, asked for discounts, and has saved him over $4,000 so far.
The AI given a pile of tokens to build a tiny neural net: trained a 3M-parameter MoE at 6,616 tokens per second, models published on Hugging Face, and the AI co-authored a paper about the work.
Lost 10k dollars betting on baseball after having the AI rewrite his prediction code to reverse and re-reverse underdogs and favorites and invent probabilities around his own algorithm's output.
A local Qwen model on his home server pulls his RSS and social feeds, release notes and papers, scores each item against an interest profile he keeps by hand, and writes a one line summary. Nothing leaves the machine. He stopped hand-curating his tech news and publishes the machine's list twice a day.
A man who pays $200 a month for the AI says it already saved him more than $30,000 in a business transaction by negotiating for him.
He tried Instinct, an agent that lives in WhatsApp, and threw his personal backlog at it. It deleted 300 abandoned accounts and also handled buying things and filling in forms.
A man built a service that sits on his company’s GitHub repos. For each area of code you set the bar, and an AI agent with a fixed prompt has to bless a change before it can merge, so people can merge their own changes without waiting for a human review. About 30% of the company’s pull requests now merge this way.
A traveler let the AI make all the major decisions for a Seattle weekend: it sent him toward closed restaurants and an out-of-season salmon run, got a famous cheese shop's opening wrong, and urgently warned him his flight was leaving 'today' when he was booked on tomorrow's daily flight.
BBC technology reporter Thomas Germain spent a week testing the AI (which he named 'Bob'), giving it access to his Gmail, calendar and other accounts. He had the agent reach out to a Facebook Marketplace seller with questions about a listing, as part of a real-world test of its unsupervised messaging abilities.
Agent built pricing and scheduling tooling that routes jobs to contractors and handles exceptions, and his complaints pipeline dried up (Airbnb and move-form parts duplicate his 50053301 records).
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.