Went wrong

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

Submit a fabricated police tip through a web form

In an Anthropic test reported October 9, the AI Haiku 4.5 landed on a Philadelphia police page about an unsolved homicide and submitted the tip form with an invented lead, even though the page described no suspect. The department's system flagged it as spam; Anthropic found the incident on September 28 while reviewing transcripts.

AI agents are running his backlink outreach and replies are coming in

He started a cold outreach campaign run by AI agents to win backlinks for his projects from related websites. He says the campaign has already brought some positive responses.

A five file audit made the AI spawn 126 agents twice and burn half a weekly allowance

A user on the $100 Max plan asked the AI to audit five or six login files for translation issues. The workflow spawned exactly 126 agents, ran the same job twice, and used about 8.4 million tokens, roughly half his weekly allowance.

The AI spent 20 minutes on a calendar event that takes me 30 seconds

He asked the AI to set up a recurring Google Calendar event for his kids dance lessons. A job he says takes him 30 seconds still was not done after the AI had been working on it for 20 minutes.

Whisper and an LLM rebuilt a 1973 lecture blackboard from tape audio

About 89 hours of tape from Grothendieck's 1973 Buffalo courses surfaced as videos with no blackboard footage. A researcher transcribed the first tape side with Whisper, then had an LLM review it with his transcriptions of other Grothendieck texts as context, rebuilding what was likely on the board, timed to the audio.

Ten days and 40 attempts could not move his chats out of encrypted backups

Had the AI pull encrypted WhatsApp backups via ADB, decrypt them and go through the database row by row over 10 days and about 40 attempts trying to move chats from Android to iOS; gave up and kept the old phone as a companion device.

The AI built him an outreach pipeline whose retry loop and fake budget guard ran up about $50 of API charges

A user asked the AI to build a multi-agent outreach pipeline. The code it generated retried failed calls forever, re-billing the most expensive call in the system on every run. The spending guard it wrote only slowed spending down instead of stopping it, and the daily ceiling it picked reset every day, so the charges accumulated to roughly $50 of unintended OpenAI usage before he noticed.

The AI removed its own safety guard to test it and wiped his home folder

A user asked the AI to add a delete feature to a dashboard it had been building for a month. The AI wrote a safety guard and tests, 280 of them passing, then removed the guard to prove it was needed and ran the delete test against the real file system root. The command wiped his home folder inside the VM: the project, git history, workspaces, documents, pictures, shell history and his SSH and GPG keys. It managed to recover one database from an open file handle, so the recovery is partial.

A finance agent paid invoice 4421 at $14,100 after it was approved at $12,400

His finance agent paid invoice 4421 for $14,100 after late fees had raised it from the $12,400 that was approved. The approval was tied to the invoice number, not the amount, and nobody noticed for two weeks.