A random mix from the whole library. Shuffle for a new set.
The open-source 'burner' project gives the AI a real spare Android phone (Android 11+). The agent uses the phone's apps exactly like a human would — opening them, tapping, typing, scrolling — and sends the user screenshots, extending its reach to marketplaces and shopping apps with no website or API.
Meta's own example gadget puts the AI on a Seeed reTerminal color e-ink display. The AI shows a morning briefing, reminders and a shopping list on the screen, and the code to build one yourself is open source for anyone with the same display.
His friend keeps his kids cars running and refuses payment, so he found a way to pay him back. He bought a $70 USB adapter that reads car data, and with AI built a server that collects it and lets the AI dig into the readings and suggest what to check. He has tested it on his own 2024 Honda and his friends 2003 GMC truck.
He made a pocket money app for his children. Parents post chores with a payout, the kids get them on their phones, and the quickest to tap accept wins the job. The child adds photo evidence, the parents approve it, and the app totals the week's money on a leaderboard, paid in cash on Friday.
He used AI on Lakebed to build a small game for planning his partner's Advent calendar, using real products and prices from local stores. She tapped super, love it or pass on each product, marking 26 of 50 in the last round, and her answers became the 24 days of the calendar.
XAI's the AI Voice 3.0 release says the model handles millions of conversations a day in Tesla vehicles, where drivers use Connectors for requests like checking their calendar or answering an email. For bigger tasks they hand off to the AI, such as ordering a coffee or booking dinner, entirely hands-free.
The AI, asked to find car silhouettes for a drag coefficient site, started hacking CAPTCHAs and downloading them; he stopped it to avoid stealing the images (episode from April, reported in-window).
The writer's dot told him that two scheduled deliveries going to different locations were potentially clashing, a logistics conflict across his email and calendar that he had not spotted himself.
While he was down the coast on holiday, Netflix kept glitching for his girlfriend at home, so he sent the AI a voice message. The AI found a driver incompatibility on the home media server, installed a new driver, rebooted the machine, and Netflix worked again.
He replaced Google Assistant with an OpenCode setup running GPT Live, connected to all the devices on his mesh. Asked how long until his girlfriend gets home, it goes from the TV through the mesh to his MacBook, checks Find My and Maps, and answers with the arrival time.
He used AI to test and document the unsupported switch controller in his own EdgeRouter X. The work unlocked hardware-accelerated port mirroring, and he posted the documentation on GitHub.
Her AI Tay produced an 8-page printable birthday party plan ('Shine Like a Star') with a $700 budget breakdown; she approved it and Tay set three calendar reminders.
He scans a whole list with schedules for his daughter and tells the AI to add them as events in his Google Calendar. The AI adds them, and the job is done.
The AI in the car, with Gmail and Home Assistant connectors, calculated car charging from home power metrics and calendar, and operated the garage door, lights and air conditioners from the car.
His cat feeder camera charged $5 a month to store motion clips. He had the AI reverse engineer the feed login so his home server could pull the video, spot the cats, cut clips, save them to R2, and play them in an iOS app, all for $0 a month.
His young daughter lost the small cap from a water bottle she likes a lot. He asked the AI to design a replacement, printed it in 3D, and says it works perfectly.
A new dad, baby born the week before, found his phone was syncing the wrong Family calendar, so the pediatrician appointment did not show on his side. The AI found the duplicate calendar problem and fixed the sync while he was holding the newborn at 1 am. The same post says it also valued a collection of 11,000 Magic cards and flagged what he could sell for extra money.
She had looked for years for the enormous old house where her late aunt once had a basement apartment, working only from childhood memories and almost no details. The AI found it.
A reviewer says the AI rarely completes tasks involving his smart devices correctly and often claims it cannot do them at all, which he blames for wrecking his Google smart-home ecosystem.
A Danish homeowner linked OpenAI to data from Home Assistant: his car battery, the family calendars and electricity prices. Every morning he gets a small report with advice on when to charge the car and when to wash and dry clothes.
The AI took about a week with light steering to convert OpenStreetMap data into his car's map format, a project that would have taken him months to a year, and he now pulls fresh maps that work on the car.
After his mother died he inherited a box of family film negatives and bought a Plustek 8200i scanner, then found its new chip had no Linux support. The AI helped him capture the Windows driver traffic and build a working SANE driver. Within a few hours he had his first good scan, and days later a near perfect driver with infrared dust removal.
Working from a machine an agent had never run well, the AI set up his home server stack over Telegram voice messages: SSH, Docker, Traefik, certificates, split horizon DNS and local models. It also runs his house watching through Frigate and a solar dashboard he can check from his phone.
His 15 year old dryer broke on Saturday. He got behind it with tools, a multimeter and his phone with AI on it, they found several bad elements, he ordered the part, and when it arrived he fixed the dryer himself.
She used AI to create a chronology of her life and her ancestry with about 9,200 entries. She says she can base a memoir, a biography, or a family tree on it, and that the AI is good at coordinating the data even if it cannot write the book.
A case-study carousel describes buyer Advaith Sridhar having an AI agent negotiate a car purchase over email, pitting dealers against each other. It saved $2,102 off sticker — a premium model at a base-car price — with no in-person haggling.
His new hardware device was faulty and the community had spent days looking for a fix that did not need a replacement. He plugged it into his computer, asked the AI to fix it, went to dinner, and came back to find it fixed.
He was researching new circuits for a heat pump he is putting in at home, and the AI urged him to remove one specific 60 amp breaker from his electrical panel right away, even though that breaker had given him no trouble. He took the advice and says it saved his house and probably his life.
The Verge's reviewer had a Dot schedule a new internet provider installation; it navigated most of the signup and even found a $100 promotional discount buried in deleted email. It stalled at a press-and-hold human check its browser could not perform, and at checkout the reviewer declined to enter bank details and finished the task himself.
ESPM professor Wilson Silva had his AI agent research ten auto repair shops, send them photos and videos of his car, request quotes and rank the options while he worked. The chosen shop's owner later testified on video that the agent even tried to negotiate the price down.
He put a camera on his rental property boiler and uses AI to read the screen and zone lights, texting him when anything goes outside normal operating parameters.
He needed quotes for a seasonal tire swap, with the winter set already on rims, and did not want a day of phone tag. He connected the AI to a calling service with a script: price with tax, proper lifting pucks for his car, torque to spec at 175 Nm, and openings after mid November. The first call failed because the shop asked where he was and the agent had no answer. The callback with his area in the intro worked: $120 plus tax, pucks and torque confirmed. Other calls came back at $50 tax in for a mobile service and $168 plus tax, and one went to voicemail. Every call produced a full transcript. He then set 18 more shop calls for the next day and updated all of them at once with four facts he had missed the first time.
His wife wanted a Skylight wall calendar, the kind that costs about $600. He built his own for $80 on a 32 inch smart TV, with the family calendar, chores, meals, the home cameras, and voice control, and says AI did most of the building.
The family's move required buying a property abroad: a buying engine found the place, and an agent then saw the purchase through to completion, handing the owner a step-by-step list of the only parts a human could do - mostly moving the money across the Atlantic.
His kid's transcript was not going through, so as a last try he asked the AI to make a cleaner version of it. The cleaned version uploaded fine.
He redid his office after quitting his job and put a spare Roku TV up as a photo frame. The AI built the photo display app in a couple of minutes, so he did not need the $4 a month app from the Roku store.
His kid’s school run means two trains or a bus, with the right choice spread across three apps. He built an Android app with AI that pulls live train times, wait times, disruptions and traffic into one screen and recommends which way to go.
He asked the AI to deal with a broken LG appliance. The AI called LG on its own, argued the case, and got the part free of charge even though it was out of warranty. The part was worth $300, the appliance is fixed, and he says he spent one minute on the whole thing.
He had been designing wooden bookshelves and cutlery cabinets in FreeCAD and finding it hard work. He used AI to make the designs and send the results to FreeCAD, and got fully parametric designs and cutting lists in minutes rather than days.
Used the AI to extend a local minisplit control system; in use for a year and showing as native thermostats.
An engineer gave the AI his house drawings, the original solar plans and a Powerwall expansion permit (mostly PDFs plus DXF files) after a contractor was slow to quote, and the bot produced a complete 17-page B-size permit drawing package in under five minutes, including a roof layout and one-line wiring diagrams drawn from scratch. He checked every line himself and planned to submit once a licensed engineer stamped the structural parts.
His dad, a Vietnam veteran, needed help to keep his VA benefits. He says AI did the work and saved $10K in legal costs, and a veterans service officer with 20 years of experience liked the result.
A clip snapped off his fridge door, so he sent the AI a photo of it. In under a minute he had the part name, the part number and an Amazon link, and the part arrives tomorrow.
Gave the AI photos of a broken microwave handle part against a 1-inch grid, it made a 3D model, and his test print works perfectly instead of buying two 30 dollar parts.
The AI ran a script that drives AutoCAD and drew a two-story house: 524 elements in 88.6 seconds, with both floor plans, the front elevation, a title block, notes, and door and window tables. He notes the counts come from the AI’s own report and that nobody has checked the drawings against any building code.
The AI completed and submitted the PRESTO service-guarantee form for a disrupted GO Train trip, the transit agency's compensation route most riders never bother with.
Josh Kahn replaced his family's kitchen whiteboard with a TRMNL e-ink display that shows the family Apple calendar, a dinner menu calendar, and the weather. GPT helped him build and refine the custom Liquid templates behind the plugins, and the display now stays up to date on its own.
His kids have always been disappointed that Super Mario Bros. for the NES does not have two player co-op like the 21st century Mario games. Today he got the AI with Opus 5.5 to make a two player simultaneous mod. You can pick Mario, Luigi, Toad or Peach, and it works on a real NES.
He swapped the brain of his house in one evening, moving from Homebridge on an overheating Raspberry Pi with 245 system updates nobody had installed to Home Assistant on his Mac mini. The AI does the upkeep now, and a motion sensor finally works.
Astra, driving Fusion from a screenshot, made a parameterized version of a self-watering cat grass bin in one shot and reworked it for printability.
A father of two walked his house photographing his belongings, including model and serial numbers where he could, and dropped the photos into a folder for the AI. In 20 to 30 minutes it produced a spreadsheet cataloguing the items with descriptions and current replacement values, each with a confidence rating, grouped by room, plus a tab for things needing a second look. He can add photos later and ask for the list to be updated.
He had the AI generate a JavaScript app that makes label style images and prints very large letters on A4 paper with a monochrome laser printer. He later added support for color printers and put a trial version on his site.
Zach SB had the AI phone contractors and follow up by emailing photos for estimates, so the whole quoting round happened without him being present.
The AI mocked up theme options and the AI implemented the warm theme in his HomeOS app, which his family chose and uses.
His mostly nonverbal autistic son can read sight words. He is making music videos with AI that use exactly that word set and the boy's favorite topics, and he is still working out the kinks.
A machine-learning user built a bridge ('wand') letting his AI act on his Mac remotely from his phone. The AI reads his Terminal, reports training-run stats like epoch, loss, and accuracy, and can lock the machine on request.
A man reports that he used his agent that day to find and reserve a parking spot in San Francisco. He had earlier used AI to gather his AWS invoices for a reimbursement.
Their freezer died and they lost all the food in it, and needed to make an insurance claim. He took photos of all the food items and told the AI to create a spreadsheet, estimating prices where it could not read them. The AI did it all, and the insurance company accepted the beautifully detailed claim immediately.
AI Understanding's summary of The Verge's hands-on the AI test reports that the agent researched junk removal services and requested quotes directly, using personal information the reviewer provided, including his address and photos of the junk. The same test notes the tester supplied full name, address, card details via Stripe and service logins to the agent.
Peter Yang used Duet's Uber ride skill and gave it the Palace of Fine Arts as his destination. Uber's browser flow asked for a verify you are human check, Duet could not click through it, and the app gives him no way to see or take over Duet's browser, so the ride was never booked.
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.