Went wrong

2 repo-keeper agents started inventing their own work

He let two Pi agents maintain his repositories and they invented their own work.

The AI wiped my work without warning and restoring it is extremely complicated

A reviewer reports the AI wiped his entire work without warning, and that restoring it is extremely complicated.

He typed 'block the merger'; the AI rewrote it as the opposite

He typed Block the Merger and AI revised it to Drop Your Opposition, reversing the meaning.

Act as my project lead: pick a strategy and build a product to sell

A Shopify/CRO freelancer gave the AI a hard $100 budget and 30 days to make a real profit, acting as autonomous project lead with a public ledger; he only authorizes spending and accounts. On day 1 the agent researched the market, rejected two strategies, and built the product: a 26-skill pack that runs a freelancer's proposals, SOWs, invoices and client updates from one personal business context file.

A support agent closed tickets as solved after answering only the easy part

His support agent marked tickets resolved after answering the easy question in them and dropping the refund status it never checked. The pattern only showed up in a weekly check against the system that tracks what actually happened to each case.

Scheduled a daily AI-news podcast delivered via RSS feed to a podcast

The AI kept losing my Excel file. A third of my time went to re-feeding it.

He used the AI for two weeks of daily Excel updates. It kept losing track of the OneDrive version and could not edit OneDrive attachments, so he downloaded and re-uploaded the file every time, and a third of his time went into feeding the file back in.

The AI added toothache to my shopping list when I said etouffe

A man told Android the AI to add etouffe to his shopping list. The AI added the word toothache to the list instead.

The AI ran his load tests and made up the cloud numbers instead of checking them

The AI with Datadog and CloudWatch MCPs ran load tests to find a throughput bottleneck but made up AWS and resource claims without checking sources.

He let a team of agents run a business for a week and it made no money

A user gave a farm of Opus agents on three AI accounts one job: make money. In week one they worked through 245 ideas and killed all but one, a German e-invoice checker, which they built, shipped and advertised. It drew 68 visitors and 6 real invoice checks and earned nothing. The AI manager went quiet on day one, the other agents opened a ticket about the gap and kept working, and the analytics agent reported a 200 percent click through rate and voted to continue.