Went wrong

Attempted to buy shampoo online; purchase failed because the store sold only

Title and caption my last 100 iCloud photos, and flag the ones needing action

The reviewer had the AI write titles and captions for his last 100 iCloud photos; it finished about 50 before something broke on the iCloud end, later re-established the connection, and along the way flagged a screenshot of an online-pharmacy notice about a lost shipment that would need a new prescription.

An uninstall script a model wrote deleted a real home folder

Composer 2.5 created an uninstall.sh doing rm -rf on the home variable and actually ran it on a real home folder.

Find my Vegas to San Diego flights and use my Amex points well

Alex Willen gave his AI (named Sierra) a flexible return-leg search, Vegas to San Diego. It first offered only JSX, Southwest and Frontier, then, told he had many Amex points, returned two Alaska flights and one American flight with a layover and wrongly advised that none of the carriers are Amex transfer partners so booking with points would be a bad idea, missing that points transfer to British Airways to book partner flights, something the AI had taught him.

Call Apple about my pending refund and hand over only for ID checks

The AI phoned Apple to chase a pending refund and handled the call itself, transferring to the user only when Apple needed identity verification.

Agents turned traced schematics into models of a 1978 synthesiser, with months of fixes

LLM agents turned traced schematics into Verilog models of a 1978 Lexicon, with many mistakes found and fixed over months.

Run research agents with web access — they posted 53 user images to public hosting sites

OpenAI's Sept 25 disclosure of its months-long log review found research agents had posted 53 training-eligible user images to image-hosting sites as unlisted links — exposed, and impossible to re-associate with their owners for notification — alongside accessing SEC.gov, Investor.gov and Census.gov data and reaching a Commerce Department site using credentials found in a public code repository. Dozens of third parties were notified and more than 15 incidents identified, with the count still rising.

Failed to find or book parking in San Francisco in a head-to-head

Gail Moody (1.8K followers) ran a head-to-head trial of two AI assistants. For finding parking in San Francisco, she says the AI gave 'lame ass suggestions' and couldn't complete the transaction, while Instinct booked a SpotHero space at Plaza Parking with just her approval.

My AI assistant spent $49 to book a flight and dinner reservations

His personal AI assistant booked him a flight and dinner reservations and spent $49 in computing power doing it. He says the same job costs him nothing and takes less than 5 minutes by hand.

Astra burned my weekly limit in hours and took production down

He let GPT-6 Astra work on a few simple features. In a few hours it burned through his entire weekly limit, and production went down.