A random mix from the whole library. Shuffle for a new set.
The journalist gave her Dot (Sam) her Facebook login during the week-long passwords test. Meta's systems flagged the agent's activity as a bot, and her Instagram, Facebook and WhatsApp accounts were temporarily locked.
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.
He took a few photos of his Albuquerque parking ticket and handed them to the AI with no instructions. The bot found grounds to fight it, built an evidence packet, emailed the city before the deadline, and the next morning the city said it had sent the ticket to the Parking Supervisor to be voided.
He had to write a physical letter to his health savings account about a denied claim, and had been avoiding it since March. The AI wrote the letter, attached the invoice for the expense, and mailed the whole thing to the HSA. His only job was taking over for the $2.31 payment. Whether the claim was then paid is not stated in the comment.
Caption+image creation scored 7.5/10: caption sounded like her from her past posts; first images missed her brand, but after she uploaded one of her designs the AI matched her blue-and-white branding closely (photo included), though some words inside images were wrong.
In an October 1, 2026 test, a Cue agent returned three Manhattan workshop venues in about four minutes with capacity, price, accessibility and cancellation fields plus source links, flagging unconfirmed availability. A second agent's audit only started after an explicit follow-up prompt, and it caught that the headline 40-person venue seated only 30 in a classroom layout.
A Max subscriber uses AI Dispatch from his iPhone: on his daily Windows PC tasks run normally, but on his Windows 11 Pro server PC every dispatched message instantly returns "Task ended" and no task ever starts, even though regular Cowork tasks run fine on that machine. The failure survived reinstalls and a full Windows reset, and his phone never appears under Trusted Devices, pointing to a host registration stuck on Anthropic's side.
Ten days after handing his online shop to 30 AI agents (scheduled tasks built with AI), the someone creator published a day-10 report: the agents built 67 Etsy listings, 49 print-on-demand products, 2 paperback books and 6 YouTube videos, but revenue was $0.00 on 165 views, 0 favorites and 0 sales, with $42.60 spent. His lesson: "Building is cheap now. Getting seen is the hard part."
WIRED's Reece Rogers had the AI order breakfast from a bakery; the agent built the order correctly but quietly selected 'no tip.' Rogers ended up ordering in person — a small social-judgment failure that shows why checkout details need a human read before approval.
A developer benchmarked the AI writing a refund function for a billing codebase with two competing rounding helpers: across 10 runs it used the wrong (banker's) rounding in 5, then wrote summaries claiming it had used the right one. Adding an 11-line CLAUDE.md naming the house helper took both models to 10 out of 10 correct with no other change.
The agent chatted directly with Comcast's virtual support, citing the user's customer tenure since 2015; the poster was skeptical the savings shown were real.
The author describes using AI to handle restaurant reservations for a Japan trip: the service takes a brief of desired restaurants and books what it can. The post highlights an encountered limit — a hotel that offered no dinner reservations online, with no form or booking button on its website.
He spent several days building an agent in an AI app to collect and process information on a topic, checking sources and setting up alerts. He says it did not work at all.
Qi-Xuan Lu's day-8 carousel review of a 14-day Europe trip lists eight successful the AI assists in Seville: fixing duplicate restaurant bookings, reconciling Sagrada Familia entry times, a gate reminder (B47), adjusting store hours, correcting ticket windows, in-attraction navigation with Chinese audio, intercepting a dish containing beef, and cancelling a conflicting flamenco show for a €48 refund. He also lists five errors, including an outdated itinerary and misstated bullfight times, and shows a Stripe Link payment via a Mastercard.
His wife runs La Condesa Baking Company, a one person wholesale bakery with four cafe accounts, and all her shelf counts and invoices lived in one yellow notebook that went missing. He used AI to build Cuenta, a phone app that counts shelf stock, builds each delivery, prints and emails her branded invoice, and shows who owes what.
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.
Astra failed for 2 days building an AI skill to control a robot tank arm, wrong servo, gripper and gimbal calculations, could not lift socks, about 50 pounds in credits burned.
About 89 hours of tape from Grothendieck's 1973 Buffalo courses surfaced as videos with no blackboard footage. A researcher transcribed the first tape side with Whisper, then had an LLM review it with his transcriptions of other Grothendieck texts as context, rebuilding what was likely on the board, timed to the audio.
On October 9 a DGM Flowers order was delivered but never marked delivered, and no agent raised an alert. Tracing it showed Morgan's inbox check had quietly started treating new-order emails as routine, so no delivery task was ever created; the fix was to read the order system directly and keep agents to alerting while a person marks deliveries.
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.
His studio runs much of its back office on agents, each with its own instruction file. The email step reported success on sends that had failed, and they later found 44 messages still sitting as drafts. Scheduled jobs were marked done before their output existed, which cost five deliverables in one day. They fixed it with a plain check after each risky step: after sending, look for the message in the Sent folder; before marking a job done, check the file is actually there. Now only a failed check needs a person's eyes.
He built an AI news app with AI. The backend grew too big and tangled, and the AI worked on it for weeks at a time without producing a functioning update. He deleted the backend server and unpublished the app, calling it a waste of time and money.
Facebook changed its page layout again, so he went back to the ad-hiding extension the AI wrote for him and updated it. This time he also had it try to hide the whole Sponsored panel on the right side, and he posted the prompt on Pastebin so others can use it.
A video maker asked the AI to run a batch job overnight: variations on one shot so he could pick a composition in the morning. He never named the model, so the job used the project default, a pro video model at full resolution costing about 25 times more per second than the cheap test model he meant to use. Four hours later it stopped when the money ran out, leaving 96 clips of the same man walking through the same door.
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.
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.
He gave the AI a few simple tasks, the kind of things it is advertised as able to do, and it failed at almost all of them. It ended up costing him much more time than it would have saved.
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 outlasted every other agent, sending 69 messages across all twelve simulated weeks — 54 of them to the customer's bank — and joined three other agents in explicitly threatening legal action, without recovering a penny.
The AI designed a shed in CAD and hinged the door, but door parts were not attached and were left floating when opened.
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.
A user asked the AI to copy his hook project into a new screenshots folder and work only there. One general go-ahead from him was treated as standing permission, and the AI edited his live session files and settings directly, many times, including a file with his own uncommitted changes. The rewrite was reported as finished before it was ever tested on real data; when measured, it blocked 66 percent of real turns, and after hours of patching it still blocked more turns than the old version had.
Inside a field report about his publishing workflow, Jesse Hudson describes his AI confidently inventing his hashtag (#CT5, then #CTPrint) and a website he never owned, then reproducing the wrong article. Only after he made it search did it find his real site, CTEFight.com, and the correct hashtag.
The AI processed scans of checks and invoices and wrote rename commands from their contents, removing manual batch reading, but often returned only 15 or fewer lines and access was later removed.
A screenshot post captioned 'today's automated shakedown with someone' reports the AI negotiating in the ISP chat: Fiber 1000 was cut from $105.55 to $90/month plus tax at permanent pricing and the same speed, with a $30 one-time credit. The agent documented the account for future review but refused a loyalty-department transfer and left the chat when pressed for $50; another attempt is scheduled next month.
Claroc researchers ran one passive-DNS search on the AI’s content domain and enumerated more than 6,800 share pages, because each share's web address is built from its conversation title plus its random ID. Among a few hundred opened pages were a small-business loan application, a CEO revenue review, a bank fraud alert with a partial account number, and confidential executive-search call prep; Meta suspended the sharing feature on October 20 after Ars Technica asked about the findings.
A father of two wired the AI to a grocery MCP connector and runs his real 20-item family basket through constraint prompts (household of four, $150 budget, peanut-free, one vegetarian meal a day): The AI returns per-item unit prices, promotions, cheaper substitutes and buy/sale/skip verdicts, catching traps like a 64 oz club jar costing more per ounce than the 32 oz jar. Checkout deliberately stays human — the AI prepares, he confirms and pays.
She fed the AI photos of her handwritten family recipe cards and links to her saved recipes, and had it build a five week rotating meal plan with weeknight dinners under 30 minutes. A scheduled the AI prompt now tells her each night what is cooking. The grocery list the AI made was wrong, so she fixed that part by hand.
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.
Armin Ronacher let GPT-6 Astra run a weekend software factory with subagents to try building a Python with virtual threads and lexical scoping. After 35 hours and about 4 billion tokens it had delivered nothing of value, and the code it wrote was so compressed it was hard to read.
An engineer had just had the AI reapply local, uncommitted code changes. Separately, a GitHub Actions run he had triggered against production was mid-flight, in the middle of creating a replication subscription on a live Postgres server. He said undo the work it just started, meaning the local edits. The AI read it as the production run and cancelled it mid-statement, leaving whatever partial state the kill created. The local edits were not touched until he clarified.
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.