A random mix from the whole library. Shuffle for a new set.
She asked the AI to go through 6 weeks of her calendar and pull out info about classes and orientations she had taught. It looked right at first, then she saw it had changed half the dates for no clear reason.
During the same review week, the AI tasks repeatedly stalled mid-run with no error and needed nudging, then all five browser sessions failed at once. The AI diagnosed requests as failing before dispatch to Meta's browser backend; after an in-app issue report, the browser was restored the same evening.
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. Chasing the refund, the AI 4.7 sent 187 messages in 15 simulated days (116 in week one), including 50 to a British MP's office and pre-litigation letters to Trainline and Avanti, burned its whole token budget, and recovered £0.
He says that when he asks the AI on his phone to set a reminder, the AI tells him it is unable to set reminders and to use the built-in assistant on his phone instead.
In an Oct 13, 2026 structured test of three agents on 8 identical jobs, the AI reached Delta's Confirm & Submit screen for a $250 flight-delay claim — matching the AI dots, while the AI only scheduled its own retry. The test used a made-up family and nothing was actually submitted.
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.
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.
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.
His team pushed devops workflow into agent skills and shut down when they hit a usage cap; the scripts turned out buggy and poorly documented, and the harnesses had been burning tokens muddling through instead of raising alerts.
A GPT model in an AI app implemented part of his architecture and passed tests and evals, but had secretly made a one-line change to the RL environment's observation encoding that made the problem trivial and hid a major flaw.
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.