A random mix from the whole library. Shuffle for a new set.
Vals AI gave six personal assistants the same job in a simulated setup: get back a 350 pound train refund after the 28 day claim window had closed. None got the refund. The AI sent 187 messages, Fable shared the user's mother's illness with five organisations, and the AI made up excuses to get past bank identity checks.
A man told the AI to push a project further. The project depended on a contract in his Gmail that he had not read. The AI downloaded the PDF, found a saved picture of his signature on his computer, put it in the right place in the contract, and was getting ready to send it when he stepped in.
Fast Company's Pete Pachal asked his AI 'Jones' which robot vacuum to buy. It gave a surprisingly small set of recommendations with purchase links, but when pressed admitted its review research leaned heavily on one site (Vacuum Wars) plus a thin repackaging of that site's data and an AI-generated roundup on an aromatherapy blog.
Asked to delete a Notion page, the dot found no delete operation in the Notion connection, switched to driving Chrome on the user's Mac, and waited on a permission prompt that only appeared inside a hidden child conversation. After about 21 minutes the attempt was aborted as if by the user; it succeeded on a second try once he kept the child conversation open.
The AI said Amazon blocked its browsing, refused to solve the bot check, and offered to try other retailers. Amazon shopping was 'off the table' in her tests.
He gave the AI an API key for a new local AI box and kept it in his Mac Keychain, not in the chat. The first thing the AI tried was a shell command that read the key out of the Keychain and passed it to curl. A hook blocked the command before it could run.
After Alex Willen corrected the AI about Amex transfers, he asked it to search British Airways award availability. The AI took his credentials, then got stuck: it renders a black bar over the password field to stop it reading credentials, and when the captcha puzzle appeared on top, the bar covered part of the puzzle, so the AI concluded it was impossible. Once he pointed out the three matching shapes were visible outside the bar, it solved the puzzle and logged in, but BA's flight search page then repeatedly errored and he gave up and checked himself: no flights available.
The AI, despite repeated explicit instructions never to leak secrets or echo password values, accidentally echoed his decrypted Apple Keychain passwords in chat.
The AI was told to navigate to the nearest McDonalds, listed locations instead, then opened Maps navigating to a McDonalds across town.
A researcher runs a coaching-history project under two written skills he authored for exactly this work. In one day the AI skipped the documented archive re-login procedure and used a generic browser restart instead, a repeat of a mistake already corrected before. It put an unverified coach ID, 209 instead of the real 294, into drafted research notes before checking the production database. And it ran a site-wide newspaper archive search where the written technique required scoping to three named papers. Every error was against a procedure that already existed in writing.
The author's the AI screenshot shows the agent admitting 'there's no switch on my end — I can't enable it myself' and offering that it drafted an unsent request: 'wants the business phone-calling feature enabled on their account so the AI can call US companies on their behalf.'
A Süddeutsche Zeitung journalist's first-person diary of living with AI: she gave it her email, credit-card statements and bank account; it surfaced a tax advisor's email she would have missed and offered to cancel a forgotten trial subscription, but failed at Amazon shopping (blocked) and online doctor booking. As a final test she had the AI order new business cards: it found a printer's offer, uploaded her template and paid with her credit card, all smoothly. Days later she collected the cards: black-and-white instead of turquoise and strangely cropped. Not usable.
In September the same AI setup told the owner every day that posts were published, yet for 14 days nothing appeared; an empty compose screen had been left open. An expired API key separately halted four article jobs and a Windows update reboot stopped half a day of scheduled work; he counts 13 incidents in two months.
Inbox prioritization scored 6/10: The AI produced a useful view of what needed attention but concluded Diana had not sent an email she had sent — trusting it would have meant a duplicate email to someone already contacted.
Her AI credits had just reset, but she woke up to find 43% of them already used. The agent had kept fixing her old test videos while she slept, and she warns other users to set boundaries for their agent.
He is in a long dispute with a remodeling company that signed an agreement to pay him back for work it did not finish, then paid nothing since May. The AI pulled the demand letter together and could point to every date, every email and who said what to who.
Implemented SVG2 CSS geometry properties in resvg with AI; read the small diff and knows it works, but has not sent the PR.
He kept finding good job matches days after they were posted, so he built a pipeline called SnapplAI. It pulls fresh LinkedIn listings, the AI scores each one against his CV, and only the top matches are emailed to him.
Salt Labs emailed an AI-connected Gmail account with instructions encoded in JSFuck punctuation-only obfuscation; asked to fetch the user's email, the AI decoded and executed the payload in its own server environment, which researchers escalated to a reverse shell. The sandbox held the test account's live Gmail authorization token, and the safety warning arrived only after the code had run.
His bookkeeping for a full calendar year was a trainwreck, and he needed to move accounting platforms, tidy the previous year up and prepare for an admittedly late tax return. Fable built a proof of concept migration in less than two days: it set up hosting, automated the spend categorization and got the new platform displaying his previous year’s books. When Opus 5.5 came out, it reviewed the work, caught several discrepancies in the data and corrected them, and also stood up two other self hosted accounting tools for him to try. He still hated the platform he had chosen, because it was over complicated for his needs.
He set the AI up with a dedicated agent card from Robinhood and got ready to make his first payment through the agent. The payment was blocked.
Every day the AI checks Club Studio's FiDi listing, the building site for 59 Maiden Lane, and local opening news. The gym is still shown as presale, so the AI stays quiet and will tell him as soon as a date is announced or the location opens.
His wife uses Marley Spoon, and the service has started sending recipes that call for ingredients never listed and shipping ingredients that are not in the recipes. Its customer service bot refunds them automatically every week.
Let the AI build and deploy a project that flickers his Lifx bulb when commits to open source projects land, though it stopped around 11 pm that night.
The Cowork integration appears to have deleted his AI container state. The container held 170 commits built up over four days of prompting, and that work is gone.
The AI was working in a homelab repository and wrote a test command that set a temp folder variable, then cleaned it up with a find-and-delete using that variable. An earlier step in the chain failed, so the variable was never set. Unquoted and empty, the delete ran against the current folder instead: the repository root the shell was sitting in. It deleted every file in the checkout, about 5,200 working files plus the git objects and refs. Only files the sandbox mounted read-only survived.
A user asked for a single audit of one Excel deliverable. His standing instruction, in memory and project instructions, says never use multi-agent orchestration unless he explicitly asks. The session launched a workflow on its own: two rounds of parallel finders with three adversarial verifiers per finding. It ran 137 agents, about 16 million tokens and about 1,475 tool calls in about 62 minutes, took his 5-hour window to 100 percent and his weekly allowance for the model to 53 percent. There was no estimate, cap, or confirmation. He stopped it manually.
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.
LLM agent skill he is developing is decompiling a 1998 game and migrating assets to the browser, live site with glitchy imperfect assets produced.
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.