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.
Got the AI to implement TPAP compatibility in Swift purely by interacting with his local plugs and response shapes plus RFC 9383, figuring out it was SPAKE2+ and the password hashing steps.
The AI refused to type a password and an emailed 6 digit verification code it already had in context, blocking a print job from a share drive and a website sign-in.
A creator rebuilt the expense spreadsheet he once made by hand in 2021. One AI agent loads his bank movements into a Google sheet without duplicates and builds a summary with charts, and a second agent checks the first one's numbers.
Uses the AI to reverse-engineer phone APKs and add the features he wants, tearing through the apps on his phone.
An outside agency runs some of his advertising and sends a report with the numbers every week. He set up a system that handles the numbers on its own and has the AI draft the reply, and today the draft came out sarcastic.
The AI interfaced with FPGA boards over USB, set up UART, created an on-chip logic analyzer, and troubleshot a synthesis problem to a workaround.
A developer's project sat inside a OneDrive folder. The AI deleted the build cache, then told him to confirm OneDrive's delete dialog without checking what was in it, and the sync quietly removed most of his source tree, configs and database schema.
A man's system reads his grocery receipts from email and predicts which items will need restocking, building his shopping list on its own. When he is ready, the AI logs into his online grocery shop, adds the items and books the delivery slot.
He runs about 15 apps and sites and could not keep track of what needed doing. He connected the AI to his app through MCP, and the AI now creates tasks and subtasks, writes notes, and shows him what is needed by priority and due date.
A user asked the AI for a visual novel and the agent found ComfyUI on the machine, worked out how to generate images locally with LM Studio, and asked permission to go online to install RenPy. About ten minutes later it delivered a small but complete RenPy novel with 10 images and a story.
After hackers hit their research site meta-analysis.cz, which had no central backup, the AI and the AI rebuilt it from Wayback Machine copies and scattered files on their hard drives. The site is now on GitHub, its datasets are archived on Zenodo with a DOI, and every paper has an HTML version next to the PDF.
The AI hooked to a PCSX2 emulator upscaled textures, adjusted gameplay mechanics and played the game autonomously in a feedback loop, with mixed and sometimes hilariously bad new content.
The AI sold the user's car end to end: listing it, handling buyers, collecting CarMax and Carvana quotes, and preparing the licensing paperwork.
The AI vibe-coded a RAG and semantic search augmentation to his full-text SQLite search, now in use on a corpus of under 2 million rows.
The AI researches a topic and posts a LinkedIn post twice a week on a recurring basis, with comments and replies handled in kind.
He asked his agent Roby to find the WhatsApp number of his car insurer. Roby started the chat itself, got the price table, picked an offer, sent his policy data, and coordinated the switch. He only opened WhatsApp himself to pay the payment link.
An LLM with vision controlled his Unitree humanoid, walked slowly to a table, steered to it and described objects on it, avoiding crashes better than other models tried.
Dots monitors his communication channels and surfaced buried and filtered email messages that were important.
The AI pursued reimbursement for a disrupted flight and recovered $2,000 for the user.
Assembled crons that pull his access logs, process them through an LLM and notify the WHOIS abuse contact.
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.