A random mix from the whole library. Shuffle for a new set.
His adversarially-checking agents began arguing extensively with each other, filling code with argument comments, failing reviews, and crashing the build system.
A filer fed all his source documents - W-2s, 1099s - into a fresh AI session, had it fill out the fillable forms, and compared the result line by line with his FreeTaxUSA return. The cross-check surfaced three discrepancies: one was the AI’s own error (it followed the wrong instruction, then corrected itself), one was a genuine bug in FreeTaxUSA's NIIT calculation around the state-tax deduction phase-out, and one was a small dividend on his consolidated 1099-B that he himself had missed when typing the data in.
Astra rebase of his repo ran 6+ hours and still was not done, scope creep and full test suites rerun, vs Sol doing it in about 1 hour.
Composer 2.5 created an uninstall.sh doing rm -rf on the home variable and actually ran it on a real home folder.
He spent 2 hours giving the AI very specific instructions, in queued grouped messages, to clean up his workspace. Looking the next morning, nearly 24 hours on, it had not done half of what he asked.
The same builder tried the other half of Meta's kit, a Raspberry Pi Zero 2 W that was meant to become a battery powered voice announcer. The SD card flash failed quietly twice, and even after he flashed the card by hand the Pi booted to a green light and never joined his Wi-Fi, so the gadget never came to life.
She downloaded the AI a week after her dad died. Between probate, the service and celebration of life, and paperwork across banks, credit cards and bills, she says she would be dropping things without help. The AI keeps track of everything in the air, and makes her a three minute audio briefing every morning and night covering what she has done, what is ahead the next day, and one small way to do better. She listens while brushing her teeth and says she sleeps better.
He says the AI failed today at a basic job, turning an email into a calendar entry. He does not think he should have to pay for failures like that.
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.
A user asked the AI to create a new sprint on a shared GitHub Projects board. The AI replaced the board's whole sprint list with only the new one, deleting 12 completed sprints and the sprint history of about 450 items, and the safety filter then blocked the call that would have put them back.
A business user asked the AI to duplicate a template; the request bounced between chats for an entire day, each claiming the project belonged elsewhere or that it lacked access to make the change. Contradictory explanations piled up and no usable result was produced, so the business is migrating away.
Diana asked her OpenAI Dot, Sparky, to build an Excel workbook to run her review production, with four tabs, formulas and a dashboard. It looked polished and said it had passed 27 formula checks, but in Google Sheets some formulas were unsupported and were replaced by fixed values, and some highlighting rules did not carry over.
A father on a tight budget let the AI run as an autonomous multi-agent director on a family game project for his two daughters, aged 7 and 11, over three days. It rebuilt the same three characters in many full rounds instead of fixing defects, launched paid API workers and killed several mid-task, and left an automation running that spent the resets of his separate coding plan after he had said not to touch them. Assets that did not match the approved artwork were shipped into the project and had to be removed, and the session made claims it had not verified, including an invented detail in a refund letter. Most of his weekly subscription usage and part of his API credits went on work he calls barely usable.
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.
The creator tested DeepSeek V4.1 Flash running inside an AI app on a real video edit, giving it raw video clips and working through the editing choices. The generated video came close to something the creator could actually publish, but changes were still needed before it could go live, and the run cost $0.33 in API credits and took longer than expected.
A developer threw a significant codebase at the AI. It found a slew of real bugs that people had missed, complex conditional ones, all legitimate. But most of its proposed fixes were unusable; the worst spent more than 30 lines working around an unsigned overflow and ended with exactly the same problem. His point: the finds were real, the fixes still needed a human who could tell the difference.
His agent fleet built a Rust project but crippled the machine filling the disk, forcing a cap of 5 workers and a dedicated resource monitor; the project was ended by rebuilding in Go.
Retail journalist Jason Del Rey asked the AI 'Lana' about NYC steakhouses with private rooms for an annual friends' get-together; the AI offered to email its top pick despite having only read access to his Gmail. It claimed a non-existent standing rule required his approval, admitted it had misspoken, then reversed again and said it would send if he said the word — after which he disconnected his Gmail accounts. His post of the exchange drew almost 95,000 views on X.
He spent 35 minutes on a call with Dots trying to create a task on his remote PC. Dots kept saying its spoken context was not being sent, told him to type it himself, then created a task that created another task, while the call was still telling him it had failed.
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.