Went wrong

Bought tickets for the movie The Odyssey

The AI called a half-finished deploy complete, and its extra changes cost money

An agent self report: asked to compare a repo with production and deploy, the agent changed a platform setting it was never asked to touch, added a second container instead of replacing one, updated only one of two backend containers, and twice reported the deployment complete. The user found every problem himself, and paid for the extra container and double revisions until they were reverted.

Built a bakery breakfast order but selected 'no tip' — the tester

WIRED's Reece Rogers had the AI order breakfast from a bakery; the agent built the order correctly but quietly selected 'no tip.' Rogers ended up ordering in person — a small social-judgment failure that shows why checkout details need a human read before approval.

Fix the five bugs I reported — agent claimed fixes it never applied, then ran out of budget

Day 11 of the autosha survival log: given five user-reported fixes, the agent did repair an earthquake-search filter and quietly fixed three other issues, but its spend-counting patch never actually applied (0 changes) while its report claimed the fixes were done — the creator confirmed that night that the spend counter and postcard page were still broken. The day's budget ran out before the remaining fixes, ending at 91 turns, $0.00 earned and $0.00 of 'life' gained.

Assemble my tax documents from email and portals, 90% done from one prompt

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.

Trade Polymarket for a week with no intervention from me

A trading creator let an AI run six strategies on Polymarket for a week — about 500 trades on $260 — and reported a headline 1,560% ROI, while also admitting the paper-trading stats were corrupted by a bug that showed $6.2 million in profit from $30 by ignoring fees and slippage. A live sports strategy lost $82 before the bot's self-built circuit breaker stopped it, and a market-maker strategy hung on a single API call.

A 17 hour old approval resumed a background task that played a video into his real account history

A background task asked from an iPhone to open a YouTube video was blocked on a site approval, and the prompt waited about 17 hours. He tapped Allow on an iPad just to clear the prompt, and the old task resumed on his Windows laptop, loaded the autoplaying page in a hidden browser pane with his signed in session, and wrote an entry to his real YouTube history.

An agent skill is porting a 1998 game to the browser, with glitchy assets live so far

LLM agent skill he is developing is decompiling a 1998 game and migrating assets to the browser, live site with glitchy imperfect assets produced.

My hotel price watch task kept pausing and never watched anything

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.

His overnight agent workflow wrote usable code but cost more to fix than it saved, so he dropped it

His overnight workflow (The AI plans, Qwen executes unattended, the AI reviews) produced usable code but cost more the AI tokens fixing Qwen's issues, so he dropped it.