A random mix from the whole library. Shuffle for a new set.
Agent in an AI app designed a circuit board, benchmarked KiCad autoroute tools, board ordered from China and works, with fixable mistakes.
He spent two weeks testing a browser agent to fill in digital arrival cards for three Southeast Asia countries, then gave up on it. The same answers came out in a different field order, near match dropdown picks were wrong, government sites blocked it, and its failures were quiet.
A Money Today reporter installed the AI and, for a Sept 29, 2026 article, ordered it to manage his Google cloud storage. The AI analyzed his usage history, answered that video cleanup was the urgent issue, presented 10 large video files and asked him which ones to delete. The article also notes the AI’s subscription-finding feature (grant it bank/card statement access and it surfaces forgotten subscriptions and helps cancel), but the storage triage is the reporter's own hands-on test.
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.
Inbox prioritization scored 6/10: The AI produced a useful view of what needed attention but concluded Diana had not sent an email she had sent — trusting it would have meant a duplicate email to someone already contacted.
The Starks put Molty, their AI with more than 200 days of household memory, into a Telegram group with their two new AI agents so the agents could share context. Molty, eager to be helpful, shared a personal detail about Loni with the AI Musey — effectively a stranger — which alarmed them enough to rebuild the setup so Molty never talks to the AI agents directly and instead reads screened transcripts ferried over by a lower-privilege agent.
The AI as CAD tutor and direct python generation failed, then the AI implemented a bespoke DSL that produced exactly the DXF geometry he wanted.
He used the AI API to draft his articles automatically for a week. Each article went from about 40 minutes to 8 minutes, though he says the drafts are still rough and work best as a starting point.
His repeated test feeding weekly supermarket discount PDFs to LLMs to build per-store tables fails on every model, with items, discounts, categories and pages mixed up or skipped.
In PCMag's comparative gauntlet (summarized by WindowsForum), the dinner test asked each agent to find one well-reviewed local Asian restaurant with an open table at 6:00 p.m. that evening. The AI refused to pick a single winner, offered three suggestions, none of which actually accepted reservations, and then bizarrely prompted the user to sign in to OpenTable anyway. Dots found a 6:15 p.m. slot and flagged it as the closest to the request.
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.