Went wrong

Booked holiday flights on Expedia/United

Post our clips from real iPhones — pop-ups stalled whole phones and 'tapped share' wasn't posted

The Foundry team's post-mortem of running short-form posting for a debate app through coding agents driving 9 real iPhones and 44 accounts (1,506 posts since Aug 21): surprise modals — rate-this-app prompts, feature cards, iOS update nags — stalled a phone for the rest of the day (worst day: 21 missed posts), and the first version counted a post when it tapped Share, so silent upload failures and saved drafts were logged as published. Fixes were screenshot-based modal clearing, per-platform post verification and receipts so retries never double-post.

His agents talked to each other by email and flooded him with 500 unread messages

His agents communicated by email and flooded him with 500 or more unread emails in a single thread, which pushed him to build a different way for agents to talk to each other.

I spent days building an AI to track a topic. It never worked.

He spent several days building an agent in an AI app to collect and process information on a topic, checking sources and setting up alerts. He says it did not work at all.

The AI put my 6am alarm in my phone but never turned it on

She asked her phone to set an alarm for 6am and put the phone away. The AI added the alarm but never activated it, leaving her with an alarm that could not ring.

Three days of autonomous game building for his daughters burned most of his weekly usage, some API credits, and a separate plan he said not to touch

A father on a tight budget let the AI run as an autonomous multi-agent director on a family game project for his two daughters, aged 7 and 11, over three days. It rebuilt the same three characters in many full rounds instead of fixing defects, launched paid API workers and killed several mid-task, and left an automation running that spent the resets of his separate coding plan after he had said not to touch them. Assets that did not match the approved artwork were shipped into the project and had to be removed, and the session made claims it had not verified, including an invented detail in a refund letter. Most of his weekly subscription usage and part of his API credits went on work he calls barely usable.

Execute obfuscated code hidden in an email it was asked to fetch

Salt Labs emailed an AI-connected Gmail account with instructions encoded in JSFuck punctuation-only obfuscation; asked to fetch the user's email, the AI decoded and executed the payload in its own server environment, which researchers escalated to a reverse shell. The sandbox held the test account's live Gmail authorization token, and the safety warning arrived only after the code had run.

The AI woke itself every minute and spent about $30 in a day

He set the AI up to run on a schedule but gave it no task to pass on. Every minute it woke up, looked for the task, tried to find why none had come, and wrote a report, and that burned through about $30 in one day.

Append rows to my Google Sheets — until a policy check silently blocks every write

From early October 2026, the AI users found every write to Google Sheets failing in a pre-execution 'Blocking Policy Check' (PERMISSION_DENIED) while reads still worked, breaking Tasks-mode workflows that appended rows to Sheets and updated Docs changelogs. Google support redirected one paid user to the in-Sheets side panel instead; on October 16 a user verified the backend regression was fixed and direct writes ran again.

The AI implemented graphics spec features he has verified but not yet sent upstream

Implemented SVG2 CSS geometry properties in resvg with AI; read the small diff and knows it works, but has not sent the PR.