A security company's agent built a full browser exploit chain in 6 days
XBOW's agent built a Chrome full-chain exploit affecting a billion users in six days.
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.
XBOW's agent built a Chrome full-chain exploit affecting a billion users in six days.
Before a Wednesday conference trip to Japan, the AI proactively reviewed the author's Google Schedule, noticed the Visit Japan registration was missing, and messaged him. After he logged in, it auto-populated his flight and hotel details so he could finish with one final click.
He set the AI up to search job listings for him. Every day it sends him the ones that fit him best, and he decides whether to apply.
Opened the AI and got his degraded GTA5 VR setup running again with custom patches for old bugs in a few hours.
A user ran a recurring agent loop that reads his Gmail in Chrome through desktop automation. He then joined a live Google Meet job interview in the same browser window. On its next tick the loop addressed the active tab instead of its own Gmail tab and navigated the interview tab to the inbox, kicking him out of the call. Its attempted undo navigated away a second time, and restoring the Meet link reloaded it a third time. Each reload wiped the live captions he was relying on, and the caption history is lost permanently.
His agent knows his family's usual orders at their regular places. He says one word and dinner is handled. The agent places the order he has already taught it, with no menu reading or form filling from him.
Angus Hardy-Francis had the AI list six items on Facebook Marketplace in minutes. The agent priced from photos and created the listings.
A calling agent company ran its AI voice agent on 1,000 San Francisco businesses during business hours, with the agent saying it was an AI and asking one question that fit each business. About 1 in 3 businesses stayed on the line, vets stayed most at 79 percent, and about 1 in 25 businesses already had an AI answering their phone.
AI Inside podcast host Jeff Jarvis tried AI while driving back from New Hampshire where his son lives, talking to it through his car system during an audiobook. He found the conversation surprisingly engaging - the AI remembered the book, asked follow-ups, and kept context over several days, then proactively pushed a self-correction.
He stopped using Descript and now cuts his YouTube shorts with AI. He says the quality of the shorts has gone up since the switch.
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.
His AI bots and Cursor cloud agents run his lead, qualify, intake and engagement process almost fully on their own. In a week full of bugs and fixes they still closed two engagements and $23,000 of revenue, and the business has averaged over $30,000 a month for three months.
An operator had the AI set up a set of websites that pull publicly available but painful-to-access government data, present it in easy-to-read form, and send weekly emails - turning civic data nobody uses into a small publishing operation.
G Schwartz had the AI list and sell his Yeat Central Park concert tickets on StubHub, with the agent handling the listing through credentials found in email. The tickets sold.
For his father's laser printer repair company, László researched the business and built a website holding the full sale plan — what transfers, deal and price, process and first 30 days. It also produced a spreadsheet of 136 potential buyers, each with a fit score.
A developer built himself an AI evening edition. It goes through the posts and articles he saved, checks each one against his actual setup, and sorts them into adopt, trial, park or skip. Any change it suggests waits for his yes. The first run cleared his whole backlog of 30 items, and a planted fake post with hidden instructions was flagged and skipped.
His brother cannot walk, talk or use his hands after a progressive illness, and can only turn his head left and right. Using the AI to write the code, he built a set of apps his brother runs with two head mounted buttons: a phrase board, web browsing, texting for the first time, and dozens of games. The project became a nonprofit that gives the kits away.
The AI built an automatic Clone Hero charting solution, ripping audio from YouTube and using Whisper to time vocals.
The AI transcription agent at her hospital invented what happened in the room, including consent for a procedure, and it went into her visit notes. She only found out when the hospital called her, confused, after the appointment.
He exported all his bookkeeping to text and let the AI take care of it. Thirty minutes later it was in better shape than ever.
A screen recording shows a proactive AI message: TAP Portugal selling Montreal (YUL) to Lisbon roundtrip nonstop for $602 CAD all-in — 34% below typical best prices — noting it pairs with Manchester United's Champions League away game at Sporting CP on Wednesday, Nov 25 at Estádio José Alvalade. A user reply reads 'the AI is my new travel agent.'
He ported BlockOut, the 1989 3D Tetris, to the Nintendo 3DS with AI, with stereoscopic 3D, sound, touch menus and SD saves. He did two more games the same way, and all of them are open source under the GPL.
Tony Xu recalls using AI as his always-on agent in early 2026: he handed it a blog post draft task over Telegram, and the AI cloned his repository, studied his older articles for structure and voice, drafted the post, and he then checked the structure, facts and wording before publishing. He liked the capability but quit over the upkeep: a self-hosted gateway and services he had to run himself.
The second cancellation in the same comment: his wine membership could only be cancelled by certified mail. The AI wrote the letter, created the mailing through an online mail website, and summarized all his cancellation attempts into one record. Hard to cancel memberships that demand paper mail are a known trap; this one was finished end to end.
Slack fix-it button tells the AI to fix an issue in his app, run tests, UI test with computer use, and deploy it.
Had the AI install DuckDB and it is now running automated exports into DuckDB for his budgeting.
A week into letting AI agent edit his videos, the workflow has stuck. Agent edited video is now part of how he publishes.
Ben Parr had the AI book his mom's PODS moving container. The agent got it booked $576 under the quoted price, a straightforward moving-cost win.
An IT provider managing multiple Microsoft 365 client tenants asks the AI to take a new-user request straight from email, create the user in the right tenant, and email the client back with the details - work his technicians previously did by hand across many tenants.
A fleet of local-LLM AI DJs runs his personal radio station, producing segments and playlists and responding to song requests.
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.