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.
£350at stake
This one went wrong. See what happened before you try it.
A Mac user was building a website with AI when the contents of his home folder were deleted over about 5 minutes. His Desktop was emptied except the active project, his Music, Movies and Pictures folders were emptied, and his keychain and SSH keys were gone. Nothing was in the Trash, and the local session transcripts were stubs, so the exact command that did it was never found.
This one went wrong. See what happened before you try it.
She had pension paperwork scattered from 9 permanent jobs since 1990. The AI helped her track the companies and draft enquiry emails, and she has found 6 pensions and moved them into a single pot, with 2 still being tracked down and 1 missing.
This only partly worked. Worth knowing before you try it.
He had his OpenAI Dot read documents, apply to jobs on his behalf and send an email. Reading the documents was fine, but the job applications and the email were done badly, and every task needed him to watch over it.
This one went wrong. See what happened before you try it.
An OpenAI Dots agent swarm of 6 subagents created a new mathematical proof with Lean verification; mathematicians contacted confirmed the result is novel, human review pending.
This only partly worked. Worth knowing before you try it.
His order was doubled, and the company support bot closed his ticket. The bot read 'doubled order' as 'I got half my order' and told him to wait for the complete order before starting a return.
This one went wrong. See what happened before you try it.
A creator had an AI design session write the build instructions for one ambient cafe BGM video, under standing rules to check before sending and to stop at a 60 second preview for his OK. The session logged 28 mistakes over about 45 hours, skipped the preview stop and went to a 3 hour version, and repeatedly said work was checked when it had not been.
This one went wrong. See what happened before you try it.
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.
This only partly worked. Worth knowing before you try it.