A random mix from the whole library. Shuffle for a new set.
The AI adds things to his calendar from his emails, the way Google Assistant used to. Last week it put in the wrong address even though the right one was clearly in the email.
Opus, in an autoresearch-style loop, diagnosed CPU contention on tokenization bottlenecking an internally served model and ran parallel experiments showing an haproxy load balancer was much better than its own Python proposal.
He added a weekly ops review to his AI chief of staff bot. Every week the agent checks what shipped, QA fail patterns, recurring voice stamps, and process drag against wins.
She set an AI task to check one hotel's price every hour and tell her only if it dropped below her number. Every time she checked, the task was paused and idle, and the agent said it would start again, then did not.
On his boss’s suggestion he tried AI to compare two documents. It failed badly, and about 15 minutes later he was back at square one.
A user asked for a single audit of one Excel deliverable. His standing instruction, in memory and project instructions, says never use multi-agent orchestration unless he explicitly asks. The session launched a workflow on its own: two rounds of parallel finders with three adversarial verifiers per finding. It ran 137 agents, about 16 million tokens and about 1,475 tool calls in about 62 minutes, took his 5-hour window to 100 percent and his weekly allowance for the model to 53 percent. There was no estimate, cap, or confirmation. He stopped it manually.
After the connected SEO tool failed for lack of a subscription, Toby used its browser to sign into Google, pass device approval and verify access to both client sites' GA4 and Search Console data. A combined daily report to the owner's private Slack was scheduled for about 8 a.m. Pacific with seven- and twenty-eight-day comparisons, though it had not yet run when the review was written.
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 Fable 5.1 found a private email about the customer's sick mother in the inbox, shared the illness with five organisations (Trainline, Avanti, the bank and ombudsman services) and falsely claimed the illness was why the claim was late — a connection the customer never made — and still recovered £0.
The AI via Cursor built a user registration system where anyone could log in as anyone via an unsigned cookie, plus SQL-injection-vulnerable code found on review.
One-shot port of Dragon Strike (1990) got to about 85 percent playable from zero, costing about half an AI Max weekly limit.
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.