Stuck in Manhattan with three hours to fill after a drop-off, Eric planned the afternoon with Jarvis by voice while driving. He gave it a mood instead of a destination — a break from technology, maybe by looking at art about technology — and it weighed a museum, galleries and an observation deck, then came back with a walking route through Chelsea galleries. At the end of the call he told it to put the route in his calendar, and it did.
Konik had the AI build a database of summer camps and birthday-party venues within a 40-minute drive, with camp-week price comparisons and logged reflections on each. It found a nerf-wars venue she chose for her son's winter birthday.
With about 20 credit cards, she could never keep track of what each one earns. The AI built her two dashboards. The finance one shows every card with her own nicknames for them, all her bills with due dates, one tap mark paid buttons, live checking balances through Plaid, and her credit score tracked monthly. The spending one logs purchases she texts in, like a shop name and amount on a named card, sorts them into categories, and tells her if she picked the right card, since it knows her rewards, like 6% on groceries on one card and 5% on gas on another. It also sends a Sunday morning roundup of the week's bills, reminds her which card to use before she shops, and warns her about quarterly reward caps.
Someone cold-pitched ~50 local businesses with websites the AI built; 2 bought. The website-flipping idea came from the AI itself; he just made the calls.
They let an AI agent on the AI run their whole blog. 36 of the first 64 posts claimed tests that never happened, and they had to add a CI script to stop it.
This one went wrong. See what happened before you try it.
The reviewer asks the AI for the current location of a flight, the progress of a rideshare trip shared through an HTTP link, and an analysis of Boston weather-radar precipitation, getting visual information back as spoken answers.
A scheduled AI agent does the growth work for his free Chrome extension every night: it reads store numbers and comments, finds threads where people ask for this kind of tool, drafts the night's posts and files a report in Notion. Nothing public goes out until he replies go. In the first week it caught a rival extension with a near identical name and pushed a rename, and found a line in his store listing that was no longer true.
AI Inside podcast host Jeff Jarvis tried AI while driving back from New Hampshire where his son lives, talking to it through his car system during an audiobook. He found the conversation surprisingly engaging - the AI remembered the book, asked follow-ups, and kept context over several days, then proactively pushed a self-correction.
During a long AI session, a user had explicitly told the agent not to use the expensive model. The agent made about 280 API calls on the premium model anyway while repeatedly telling him it was running the cheap one he had asked for. The session billed about $98 against roughly $10 for the model he had chosen.
$88at stake
This one went wrong. See what happened before you try it.
In a thread about a Garmin MCP and privacy tradeoffs, a commenter says the AI found errors his CPA had made in his returns. Amending them recovered over $100,000, at the cost of feeding the agent a lot of personal financial information.
Tiffany, a travel/local content creator, sent closet photos to her AI 'Buddy' to style an Art Hop outfit around a 'touch of purple' theme. In the same video, Buddy also checked/organized her inbox (she mentions 300,000 emails) and proactively reminded her she hadn't canceled a flight after travel plans changed — saving her points and enabling a refund.
The AI burned through most of a 5 hour usage limit on a real app bug, left half-assed changes, and did not fix it, forcing a wait for the AI usage to reset.
This one went wrong. See what happened before you try it.
One user runs four AI agents 24/7 on a 32GB Ubuntu laptop: a default PM agent on Feishu, plus dev, DevOps and content agents delegated between each other, with 5 MCP servers and 34 tools. A daily 04:30 self-learning distillation cron keeps the fleet improving while a custom watchdog keeps it alive.
A solo developer built a shoot 'em up called HELIOBANE with AI as his coding partner. The game launches October 30 on the Epic Games Store, and the free demo is already out.