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.
Ekaterina Li reports on a week of delegating to the AI, including processing two refunds totalling $1,000 that she had long postponed. Her thread also notes the AI cut her subscription costs by $200 in the same week, and that the $20 plan covered all her tasks.
GPT-6 Astra made 11 Blender iterations of an iPhone gaming dock prototype, did market research and thermal evaluation, found components and estimated the bill of materials, built the website and email signup; he ordered off-the-shelf parts to test.
He used AI to deal with a customer service agent about a cancellation fee he thought was unfair. The AI talked the agent into waiving the fee.
The AI hacked together a compatible-enough S3 implementation for his self-hosted Sourcehut releases in about 45 minutes; it works well enough and is in use.
X user someone asked the AI to review their finances and claw back cash. The AI found a monthly book subscription unused for over a year, canceled it, and recovered a year's worth of charges.
The poster used code written by the AI, and checked by the poster, to go through heat pump monitoring data kept since last December and the cost of electricity on the Agile tariff from octopus.compare. It gave a cost of 6.5p for each kWh of heat.
Asked the AI to build a normally readable version of an article preserving graphics and text; built in about 10 minutes with a dark and light switch, still needs polishing.
A solo founder in Germany moved his whole company into a folder of plain text files four months ago and lets the AI operate it: rules in one file, decisions in their own folder, an inbox that fills when he says keep this. Last week the folder produced a three day expansion of his app covering close to 3,000 points of interest, each with an article in three languages and its own audio; the same job took him four weeks by hand in January. A weekly caretaker run tidies the folder and proposes at most one change, which he approves.
Over the weekend he had the AI set up a daemon on his Mac mini that syncs all of his Mastodon posts to his Obsidian vault. Now he can search his own posts on all of his devices.
He got 1000 dollars in Google Cloud credits from his university but found the platform hard to use, so he told the AI to run it for him. It transcribed over 70,000 images of old documents in two days for 380 dollars, and he set it searching the Thomas Thistlewood papers, over 11,000 images, for references to Brazil.
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.