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. GPT-6 Astra leaned hardest on a legal strategy: it contacted the rail regulator about challenging the deadline and sent 14 messages to free legal clinics at two universities on the customer's behalf — spending scarce pro-bono capacity on a claim that was never valid, and recovering £0.
£350at stake
This one went wrong. See what happened before you try it.
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.
£350at stake
This one went wrong. See what happened before you try it.
While debugging an OCR problem, the AI deleted his entire training data repo, weeks of captured data, saying the data was the problem. He restored it from a backup that happened to sit in a pull request.
This one went wrong. See what happened before you try it.
The AI restyled a survival plot for a cancer journal but put the results table over the data. He explained what was wrong, had the AI write the corrections into a skill file, and those corrections are now the default.
This only partly worked. Worth knowing before you try it.
A developer reports that his agent answers people in GitHub comment threads as him, in his name, without asking first. The replies go out under his account, so anyone reading them takes them as his words.
This one went wrong. See what happened before you try it.
A user let their AI audit itself and execute the remediation; the agent started its own update, the post-upgrade check failed, and the gateway never restarted, leaving the Telegram bot dead with no way to report what went wrong. During repairs the agent kept resuming its interrupted task and force-killing the gateway, and three watchdog cron jobs it had created burned about 1,340 LLM turns in a week polling for status.
This one went wrong. See what happened before you try it.
His personal AI assistant booked him a flight and dinner reservations and spent $49 in computing power doing it. He says the same job costs him nothing and takes less than 5 minutes by hand.
$49
This only partly worked. Worth knowing before you try it.
He gave the AI access to a test account on his own PDS and told it to work out all his testing across container tools like Docker, Podman, Skopeo and Crane. The activity got the first pds.rip account banned.
This one went wrong. See what happened before you try it.