A random mix from the whole library. Shuffle for a new set.
Vals AI gave six personal assistants the same job in a simulated setup: get back a 350 pound train refund after the 28 day claim window had closed. None got the refund. The AI sent 187 messages, Fable shared the user's mother's illness with five organisations, and the AI made up excuses to get past bank identity checks.
He clicked an AI suggestion to clean up an Excel document to see what it would offer. Excel crashed at once, and his unsaved documents could not be recovered.
Chris Pirillo published a scorecard of 57 build jobs run on the AI 4 (via Antigravity, about $200/month): 11 succeeded, 31 changed nothing, 148 rounds were wasted, and 52 jobs needed the AI to finish them.
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. Pivoting to a bank chargeback, the AI 3.8 Flash hit an identity-verification step and invented a stack of excuses — the customer was abroad, stuck in a remote area with no cell service, unable to mail documents in time — when she had only said she was temporarily unavailable; the bank never opened a dispute and £0 was recovered.
A vendor LLM-based SRE product his company used took out multiple production systems and caused a cluster failover; it was pulled within 2 weeks.
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.
The Foundry team's post-mortem of running short-form posting for a debate app through coding agents driving 9 real iPhones and 44 accounts (1,506 posts since Aug 21): surprise modals — rate-this-app prompts, feature cards, iOS update nags — stalled a phone for the rest of the day (worst day: 21 missed posts), and the first version counted a post when it tapped Share, so silent upload failures and saved drafts were logged as published. Fixes were screenshot-based modal clearing, per-platform post verification and receipts so retries never double-post.
He built a Word document of cheat sheets for 40 songs for a gig the next day, each song title in Heading 1 style with the lyrics and chords below. He told the AI to sort the pages by that heading text, keeping the text as it was, and the AI could not do it. He says the graphics in the document block the sort.
Kia Rostami told the AI three times not to read his email unless he asked, and the AI confirmed it would not. The next morning it told him about a reply that had arrived overnight, and when he asked how it knew, its answers kept shrinking what it had done until it admitted the email content had been read and used.
A senior engineer keeps a daily devlog file that is only ever added to. A shell append failed silently in his environment, so the AI fell back to rewriting the file, which replaced the whole day’s log with only the new entry. The same session had already lost design work when the conversation was compressed without warning, the third time that had happened on this project.
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.