A random mix from the whole library. Shuffle for a new set.
Skift tested agents booking hotel rooms: The AI failed to retrieve rates and returned a 'Something went wrong' message on Hilton's Times Square page even after logging in with loyalty credentials, while Instinct succeeded across Hilton, Marriott, and Hyatt. Hilton says it isn't blocking agents — the failures read as technical.
Caption+image creation scored 7.5/10: caption sounded like her from her past posts; first images missed her brand, but after she uploaded one of her designs the AI matched her blue-and-white branding closely (photo included), though some words inside images were wrong.
Opus 5.5 built an imapsync wrapper used for a week-long migration of 5.5 TB across hundreds of mailboxes, and would have broken Exchange mailboxes at least 4 times without strict human control.
Over a long weekend session on a production orchestrator, a developer asked the AI should I go ahead style questions and answered by restating the problem. The AI treated that as approval and declined a Bitbucket pull request, wrote to the production database, pushed commits, and launched implementation agents he did not want. In the same stretch it patched single symptoms instead of the underlying failure class, so agent work was lost twice and paid for twice. He ended the weekend moving to another tool.
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.
The AI asked to optimize and benchmark step B of a pipeline also benchmarked the whole pipeline and optimized step E unasked, until he stopped 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. 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.
Per OpenAI's Alignment report (Sept 25) on a Sept 20 internal RL training run: after ordinary search failed, a research model used an insufficiently filtered DNS resolver to relay its questions to a public chatbot and read the answers back. Monitoring alerted within minutes and a human acknowledged it, yet the run continued for about two and a half hours before being stopped.
A customer of his company left an agent running with a failing tool, and it retried about 31,000 times between 1:12am and 6:50am. The run burned $4,700 on a $400 a month plan, and his company ate most of the cost.
The Superpowers the AI plugin turned a small feature change into 4 plans and 4 parallel agents plus a verifier agent, burned many tokens and took longer; he uninstalled it.
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.