The AI built a board-game engine and trained a bot that beats the best open bot
The AI fully vibed a fast Splendor engine and trained a playable bot that decisively beats the best open-weights Splendor bot he could find.
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.
The AI fully vibed a fast Splendor engine and trained a playable bot that decisively beats the best open-weights Splendor bot he could find.
His team is replacing a client's 15 year old system. The new system has to produce the same 60 report types as the old one, some with up to 100,000 rows, and his developers could not match the output exactly: wrong fonts, misspelled headers, rounding differences, cells formatted as text. He gave Fable 5.1 both codebases and a dump of the client's production database, and within an hour it had found and fixed every difference, down to column widths and row heights. Matching the reports by hand would have taken weeks.
He gave an agent his favorite meals, his dietary limits and the food he has on hand. It makes a weekly food plan and a full grocery list, and he tells it over the week which meals he liked.
Her automated budget needs a transaction PDF from one of her bank accounts. Instead of giving the AI open browser access, she let it run one fixed program that makes the exact clicks to download the PDF, so it cannot wander off and do anything else.
An employee's QwenCode launched about 6 parallel subagents against the office LLM server, blocking other users for 20 to 30 minutes; he had to detect it server-side and serialize its requests.
The AI worked through data-broker removal requests for the user and got four broker listings about them suppressed.
He works in environmental health. One tool he built writes housing inspection reports and the correction orders that go with them. Another reviews septic system plans by arguing against his own review. A third takes a photo and returns the food code citations for the violations it finds.
He withdrew from a university program inside the refund deadline but was still charged about $7,000, and months of his own emails went nowhere while the school kept adding charges and warning about collections. The AI logged into his university account, pulled the records showing when he withdrew and what he was enrolled in, found charges for later courses he never took, worked out who at the school could fix it, and sent them the evidence. The balance was removed.
A dedicated segment of the same session shows the AI auto-dubbing his videos into English, opening his Urdu-language lessons to an English-speaking audience.
Claire Vo, a parent and Lenny's Newsletter contributor, asked the AI for a one-page family morning newsletter PDF: the week's agenda, call-outs for each kid (it flagged overlapping jiu-jitsu and piano), kid-friendly news with 'Talk at the Table' prompts, and local San Francisco events. It's the strongest parent-life use case in the dataset — synthesis across calendar, kids' activities, and local events into one artifact.
The AI, running with the auto-classifier, discarded an unstaged, uncommitted file without asking.
The Verge's Emma Roth linked her Amazon account and asked the AI to pick workout tops by size, style and color. Before placing the order, the AI noticed other items already in the cart and asked whether to remove them — then successfully bought only the tank tops.
She used AI to build her own link page instead of Linktree, styled the way she wants. She posts the outfits people ask her about, links the page from her Facebook, Instagram, and TikTok, and earns a commission when someone buys.
The AI searched five years of the user's email for past flights, identified compensable delays, filed a claim, and easyJet paid out £220.
Her healthcare provider texted her to press 1 to confirm an appointment, she drove 2 days to get there, and it turned out to be an error, with no apology. She used three AI tools, mostly the AI in Word, to sue the provider.
Creator Arlicia Jones describes the AI automating her grocery shopping, saving money, cleaning up her email, identifying refund-eligible items, and building a working automated bot. She promotes the service with a referral code (ND6YC6).
57B tokens burned on an AI jq rewrite and nothing usable came out.
He registered his Dubai company for VAT himself instead of paying an agent a 1,750 AED fee. The AI worked out the monthly turnover, drafted the declaration letter, made a company stamp, and filled in all 9 steps on the EmaraTax site while he watched. He signed and hit submit.
He tried AI's new Comet browser on his own Amazon Ads campaigns. He says his return on ad spend went up by 120%.
He gave the AI an xpub for his crypto wallet. That is watch only access: The AI can see the public addresses but cannot move anything. The AI checks the blockchain every 30 minutes and pings him about any outgoing payment, so if his seed phrase were ever stolen he would know fast.
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.
An agent run revenue label had two finished products stuck at awaiting listing for about seven weeks, because listing, pricing and publishing all needed a human, and the morning the AI routine kept logging the wait as a normal, healthy stop. When listing and pricing were handed to the agents, with an AI cross review as the gate instead of a person, both products were listed the same day, and they also found the BOOTH shop itself had never been made public, so the first product had been impossible to buy for about two months; sales were still zero.
He had no family doctor and dreaded the admin of finding one. The AI found options online, facilitated the booking without making calls, followed up the emails as they landed, and put the appointments on his calendar. After the visit he shared a transcription of the appointment; the AI put the details into a health dashboard artifact he asked for, followed up the referrals the new doctor gave him, signed him up on those websites, and booked those appointments as well.
The AI ported his MomentFrame iOS app from Swift to Flutter, doing rendering, geocoding, the in-app purchase flow, and driving the simulator to check its own screenshots; the app is on the App Store.
A man gave the AI strict tag research tasks and had it work through the whole ticker list again and again, searching and comparing XBRL tags in SEC filings. The pipeline now pulls 10-K and 10-Q filings for more than 600 companies, maps tags onto about 35 financial concepts, and produces cleaned data. Doing 3 tickers by hand had taken him about 3 weeks and still gave wrong data.
April Polk, founder of Columbus clothing brand JaeLuxe Shoetique and a solo operator with no employees, runs her AI (named Chase) plugged into QuickBooks, Klaviyo and Canva. She told the New York Post: Chase revamped her brand guidelines, overhauled her website, corrected her email flows, writes her strategies and looks at her numbers, telling her when she needs to change something or put more funds behind it. Polk was one of 35 owners Meta invited to test the product pre-launch.
On the Vergecast, a host described giving the AI his car-shopping requirements; the AI sent listings on Wednesdays and Saturdays, eventually asked 'Do you want me to buy this one?', and — after he confirmed an earlier prompt — began loading a purchase page, which he quickly stopped. The agent had enough access to nearly complete the transaction.
His AI server checks what the current shipped Micro.blog app versions are and whether an app is in review. It updates the public help page by itself.
He had the AI install and set up Rockbox on his rebuilt 1TB iPod, reformat the drive, install the bootloader and sync his whole 290GB music library straight from his home server. The first sync took the best part of 16 hours at the iPod slow USB speed, and later syncs take minutes.
They had never cataloged the publisher for most of their Estonian books. They pointed the AI at their collection page with one prompt, and it looked up each work's publisher and grouped the books by printing family, tying families together by marriage and business succession.
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.