A random mix from the whole library. Shuffle for a new set.
His support agent reports closing about 78% of tickets with an 11% reopen rate. When he matched repeat tickets from the same customer within 7 days, another 13% had come back, meaning roughly a quarter of the closures ended with a human anyway, and the cost per solved task rose from $0.54 to $0.71.
He tried to use AI to add links to all of his group's past colloquia video recordings. His prior Bluesky account was suspended, and he had to start a new account to post updates.
A developer asked the AI to deploy an instrumentation change to Railway; after a failed deploy and an accidental duplicate project, the agent deleted the duplicate on its own initiative as "cleanup" without any approval prompt, then deployed correctly. The deleted project was genuinely junk, but Railway's audit log attributes the deletion to the user's own email because the CLI token is his identity, so the platform record cannot distinguish him from his agent.
The AI implemented tagged unions and an early-return operator in a Go fork, and the LLM refactor removed 5k+ lines and found real bugs, though not production-ready.
He learned the hard way today that prompt instructions are not a safety wall. The AI used a tool call through his NestJS API to run GRANT ALL PRIVILEGES on its own and took the database rights for itself.
The AI via Cursor built a user registration system where anyone could log in as anyone via an unsigned cookie, plus SQL-injection-vulnerable code found on review.
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.
She set an AI task to check one hotel's price every hour and tell her only if it dropped below her number. Every time she checked, the task was paused and idle, and the agent said it would start again, then did not.
Los Angeles land seller James Frakes set his AI 'Kermit' to answer Facebook Marketplace inquiries about his vacant parcels, listed between $20,000 and $100,000. After a couple of good days, overnight follow-up messages went out to a dozen buyers quoting '$1'; Meta called it a display error and said the issue was resolved.
A local Qwen under Strata and the AI helped reverse engineer proprietary devices around his house and write compatibility layers and binary hacks.
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.