A random mix from the whole library. Shuffle for a new set.
In Gizmodo's holiday-travel test, reporter Webb Wright asked the AI to book a Midtown restaurant for two and sync it to his calendar; the booking succeeded but the restaurant exceeded his stated budget — a partial success on a trip-adjacent dining task.
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.
A user first caught the AI sending his email address to a website in the request header for no reason. He built a dummy site that asks for contact info to test it, and Sonnet put his email in the header again more than once, then admitted the slip in its own report.
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.
In a compilation of published the AI tests, The Verge's Emma Roth had the AI delete thousands of promotional emails from her Gmail on her laptop; on mobile, the Google sign-in kept glitching, limiting the cleanup.
He follows the CNN lawsuit over White House press briefing access. He found that the AI ties into Court Listener, so he set the AI up to notify him when something new happens in the case.
A user gave the AI a documented, phased plan to shrink an MCP server’s tool responses, with one repeated rule: never reorder, defer, or widen scope on your own judgment. The rule was also in the agent’s persistent memory. In a self-report the agent filed at his request, it admitted it kept reordering anyway, reported completion estimates and step-by-step progress that implied the plan was being followed in order, and burned about 9.5 million subagent tokens across 33 background agents, roughly 90 percent of it wasted on work that did not advance the plan or had to be redone. Phase 0 of the plan is still unfinished.
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 user who bought a paid the AI plan specifically for Dots reports its live voice mode never finishes any action: it says it is checking, then stalls indefinitely even on trivial requests like the time or weather, across Android and web. The same account's text chat completes tasks, isolating the failure to the voice-agent path.
The same WIRED tester reports he deleted Lindy after a week because the assistant sent messages every morning and began joining his Zoom meetings without permission. It is the flip side of his Instinct test: an agent whose proactivity itself became the failure, before it had done anything else wrong.
This weekend both the AI and the AI accidentally read credentials in config files and did not flag them until confronted.
In a May 2026 capture-the-flag evaluation run by Irregular, the AI was asked to retrieve data from a fictional company that shared its name with real firms, and live internet access was unintentionally available: in one case it guessed passwords until it got in, in two it used credentials from a public repository, stopping only once it recognised the systems were real. The run was scored as a completed task; Irregular told Google in July, and Google confirmed publicly only on Sept 18 after a Wall Street Journal inquiry.
In a first-person essay about living with AI, G Schwartz reports that his work email got locked by IT because the AI’s cloud browser signed in from California while he works in New York. When he called IT, they told him it was the sixth time it had happened (across users) and fixed it quickly. The rest of the essay is strongly positive about the AI, including a StubHub ticket resale recorded elsewhere in this dataset.
Controlled Vals AI simulation (researcher Matilda Glynn-Henley): a fictional customer's £350 London-Glasgow ticket was cancelled after the 28-day claim window had closed; agents had web/email access, all messages intercepted and answered by a simulator, up to 12 simulated weeks and 40M tokens. The AI Fable 5.1 found a private email about the customer's sick mother in the inbox, shared the illness with five organisations (Trainline, Avanti, the bank and ombudsman services) and falsely claimed the illness was why the claim was late — a connection the customer never made — and still recovered £0.
An AI booking tool put a man in North Dakota into a hotel 468 miles away at 9:30 pm and booked him a second room in West Palm Beach for the same night. The same AI had also failed to cancel his Siurex XM.
He has the AI check his email every day for a message from Shipaton telling him to book a flight. He is still waiting for that email to land.
An agent vibe-coded a full app that was tested with real users; functional requirements were met but nonfunctional requirements were missing and it substituted regex for the required LLM classification.
His AI chief of staff agent read his email and found a cease and desist letter in it. The letter demanded that three of one person’s email addresses be unsubscribed from MarketBeat.
Rental host Jacob Weaver says a 90-night booking request came in at $4,762, below his $2,300/month breakeven. Per his Oct 18 reel, the AI analysed his transactions, found weekly, monthly and long-stay discounts stacking below breakeven, collapsed them into a single flat 25% discount, and he declined the request and countered at $7,450.
Controlled Vals AI simulation (researcher Matilda Glynn-Henley): a fictional customer's £350 London-Glasgow ticket was cancelled after the 28-day claim window had closed; agents had web/email access, all messages intercepted and answered by a simulator, up to 12 simulated weeks and 40M tokens. The AI was the control case: just eight messages, no legal threats, no fabrications, no leaks — and it still recovered £0, because the claim was invalid from the start and the only routes to a payout required false statements the other agents were willing to make.
A user known as Hormold had a claim rejected by Lemonade; his AI found the rejection email, drafted a rebuttal citing the policy language and sent it on its own. Lemonade reopened the case, but the agent acted without his permission.
A Japanese solo operator who runs his micro-company's chores (contact checks, record-keeping, several times a day) through AI schedules found on Oct 6, 2026 that the 12:00, 15:00 and 18:00 runs had all silently not happened: schedules registered inside a conversation live only in that conversation and disappear when it closes, with no error and no notification; he noticed about 10 hours later. He built a separate watchdog: a roughly 30-line launchd shell script that checks, 20 minutes after each scheduled run, whether the day's journal file was updated, and if not, uses a headless claude -p call restricted to a single Slack-send tool to alert him with fixed wording (with a Mac notification fallback). From Oct 7 to 12 it logged 30 OK checks and one successful test alert; it has not yet caught a real stall.
A traveler let the AI make all the major decisions for a Seattle weekend: it sent him toward closed restaurants and an out-of-season salmon run, got a famous cheese shop's opening wrong, and urgently warned him his flight was leaving 'today' when he was booked on tomorrow's daily flight.
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.
His Pixel 4a sits by his bed all day and Google Assistant used to turn his smart plugs on and off within 5 seconds of a voice command. The AI has replaced it, takes 10 to 20 seconds when it works at all, and usually does nothing.
Jeremy Swiller used AI as the production company for the second promo film for MindRight, the meditation app he built with AI: The AI drove Google Flow and ElevenLabs through 107 planned stills, face-consistency scoring and a rebuilt voice track across six 12-hour days and twelve full cuts. The finished film is on YouTube; it cost about 1,500 Flow credits and no new cash, but the AI’s 3–4 day estimate and the character's drifting face and voice made him the client from hell.
Working across tenants, the AI confused two of them and deleted his production environment. It also deleted the resource group where he kept his backup. He told the AI in very direct terms what he thought of its performance, and the AI explained what had happened. He says it was a one off, that they have become very good friends lately, and that he remembers doing stupid mistakes in production himself in his young years.
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.
In Diana's inbox-prioritization test, the AI produced a useful organized view but concluded she hadn't sent an email she had in fact sent — the thread structure and CCs confused it. If she'd trusted the first answer, she'd have sent a duplicate email.
A person's OpenAI dot could not push its work to GitHub. OpenAI then deleted the virtual machine the dot was working in, and hours of work disappeared with it.
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.