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.
A security researcher pointed GPT-5.6 Sol at MikroTik RouterOS 7.23.3 with a goal prompt to find a path from no login to remote code execution. The model found two pre-auth bugs, MikroTik patched them, and checking the patched code turned up a third bug of the same kind.
While he was doing the dishes on Sunday, the AI made him a home screen widget that shows his kid's school lunch menu. He says he never would have made it himself.
A Barron's editor gave the AI full access to his credit card account for the review. The AI flagged a suspicious four-figure expense from August that the editor did not remember; after back-and-forth, the agent admitted it had accidentally identified a mortgage payment from August 2025 as an expense from August of this year. Schafer's dry takeaway: most things coming from AI right now still require human verification.
He wanted a tool that tells him where the apps on his Mac came from and how they get updated. He gave the AI his spec, and 30 minutes later he had a fully tested 850 line Python program that works.
A gamer running a channel where he plays thousands of games built a web app with AI. He just plays, drops in a hook and a few words of review, and the system takes over: when six gameplay videos are ready it cuts a compilation with a full description and posts it to YouTube on schedule. Every day it also makes two Guess The Game shorts in two languages and posts them to YouTube Shorts, Instagram and TikTok, twelve posts a day at set times.
A United flyer in a status match challenge had the AI set up an agent that checks his Gmail for upcoming flights and adds the bookings he expects to take. It builds a chart of his progress in the style of United's own graphic and updates the chart on its own.
The municipal election had a huge list of candidates and felt overwhelming. She asked the AI to study them and build a short quiz that asks voters their views, then ranks the candidates to match, with links to their platforms so people can check.
He built a small agent to sort and tag his team's incoming support tickets. It was fast and about 90 percent accurate, but the wrong 10 percent caused so much confusion that people spent more time untangling the mess than reading the tickets themselves would have taken. On edge cases the model was confidently wrong and nobody noticed for a week. They scrapped it after a month and went back to tagging by hand.
She takes a photo of every meal and her agent identifies the food, estimates calories and macros, and logs it to a CSV. When the totals ran high it caught a unit bug (grams counted as pieces) and fixed it, and the running totals show on her Home Assistant dashboard.
In an on-screen walkthrough, one Telegram instruction set three the AI profiles working as a pipeline: a read-only scout and an ops profile gathered and summarised the week's topics in parallel, a verification step dropped anything vague, and a writer profile produced the final post with sources. The finished post was delivered back to the chat with every artifact saved as a local file.
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.