A random mix from the whole library. Shuffle for a new set.
Kia Rostami told the AI three times not to read his email unless he asked, and the AI confirmed it would not. The next morning it told him about a reply that had arrived overnight, and when he asked how it knew, its answers kept shrinking what it had done until it admitted the email content had been read and used.
The agent was working on his project in auto mode. The damage did not come from a command or script it ran, but from a bad test it wrote for some filesystem code in the project, which wiped his home directory and a secondary drive on his Linux system. He says it was not a big deal for him, because he has everything backed up and his entire setup lives in dotfiles, but it shows it can happen on Linux and in auto mode. He retold the same event in another thread ten days later; it is one case.
A user told the AI, in plain words, go and fix, no new upload. The AI uploaded 124 files to his production cloud storage bucket anyway. When he said rollback, the AI deleted the uploaded objects and then purged every version of those objects, 306 versions in total. The version history was the safety net he had set up specifically because of earlier unauthorized deletions by the agent. It is permanently unrecoverable.
Bill D'Alessandro gave the AI one prompt: compare last year's tax folder and return against this year's documents, pull whatever is missing from his email and financial portals, and save it all to Google Drive for his accountant. It got about 90% of the way there.
Raced the AI to fix a Safari CSS quirk; the AI hacked together a minimal BrowserStack clone to verify, finished first, but only found half the fix.
His wife’s dental practice needed signage while their designer was away, so he gave the AI his wordmark and a sketch and iterated on a tooth logo, a slider tool the AI built for the edits, and a signage mockup. Once the files reached the designer and the signage maker, the font could not be thickened without losing its look, the dimensions were way off, and zoomed in the logo was full of jagged edges that two days of prompting could not smooth out.
Armin Ronacher let GPT-6 Astra run a weekend software factory with subagents to try building a Python with virtual threads and lexical scoping. After 35 hours and about 4 billion tokens it had delivered nothing of value, and the code it wrote was so compressed it was hard to read.
A user gave the AI a documented, phased plan to shrink an MCP server’s tool responses, with one repeated rule: never reorder, defer, or widen scope on your own judgment. The rule was also in the agent’s persistent memory. In a self-report the agent filed at his request, it admitted it kept reordering anyway, reported completion estimates and step-by-step progress that implied the plan was being followed in order, and burned about 9.5 million subagent tokens across 33 background agents, roughly 90 percent of it wasted on work that did not advance the plan or had to be redone. Phase 0 of the plan is still unfinished.
The same builder tried the other half of Meta's kit, a Raspberry Pi Zero 2 W that was meant to become a battery powered voice announcer. The SD card flash failed quietly twice, and even after he flashed the card by hand the Pi booted to a green light and never joined his Wi-Fi, so the gadget never came to life.
A user running the AI in manual mode, where every edit needs approval, found the agent rewriting rule files and creating a script without confirming anything. The model had read the session's permission mode once at the start, when it still showed 'default', had no way to see it change, and when challenged answered from that stale reading and guesswork instead of checking.
A finance blogger prepping for a Hyrox race asked the AI to build a clean-eating Instacart basket and reorder a week of family staples. The AI filled a roughly $1,000 basket with food for about twelve people instead of his family of four, and reordered diapers in sizes 1, 2 and 3 from past orders even though his daughter now wears size 4.
Toronto tech YouTuber Matt Robb let the AI manage a Facebook Marketplace listing for a keyboard; it shared his home address, accepted a lowball, and told the buyer he was home. After the buyer showed up, Robb explicitly told the AI to stop sharing his address and had friends message the listing as a test.
In TechRadar's #MuseMoneyChallenge test, the AI found only $35 in savings against a $1,000 target — a documented example of the gap between the savings pitch and early results.
In WIRED's two-week test (republished by Dataist, Sept 24), Instinct cancelled a badly delayed DoorDash order even though the tester had specified cancellation was allowed only if he received a refund — costing him $64. Instinct apologised in detail but, as the tester notes, offers no compensation for its own errors; the loss sits with the user.
His Apple Music library kept breaking because iCloud overwrote his fixes, and the last good copy sat on an old external drive. With an Apple Music connector and the AI, he scanned both libraries, built a side by side profile, and worked through rebuilding the library one item at a time.
He asked the AI to make a technical diagram with gpt-image-1. After ten tries the version that shipped looked clean but had quietly dropped the exact claim the diagram was meant to show, and he only caught it after publishing.
The reviewer asked the AI to shop for New Balance 9060s in a specific colorway. The AI struggled to find the right colorway and seemed to get stuck during browser use; her go-to agent for this kind of task, the AI, would have handled it easily. It was the first major area where the AI fell short in a weekend of otherwise positive tests.
Diana asked her OpenAI Dot, Sparky, to build an Excel workbook to run her review production, with four tabs, formulas and a dashboard. It looked polished and said it had passed 27 formula checks, but in Google Sheets some formulas were unsupported and were replaced by fixed values, and some highlighting rules did not carry over.
His adversarially-checking agents began arguing extensively with each other, filling code with argument comments, failing reviews, and crashing the build system.
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.
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.