Went wrong

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

Make my $1,500 rent in 30 days — CEO agent spawned a swarm that burned all tokens in 10 minutes

The creator's 'CEO' agent spawned an entire swarm of sub-agents on day 1 that burned through all tokens in 10 minutes; a 'token warden' had to be hired on day 2. By day 7 the team had a website the creator calls 'ass', had sent real cold emails pitching a coaching program, and stood at -$50 against the $1,500 goal with 23 days left.

His models rebuilt a dead mobile game's fight screen near pixel-perfect

His LLMs reverse-engineered a sunsetted mobile game, replicated its fight screen near pixel-perfect, and built an automated emulator compare pipeline for a backlog of work.

The AI bricked his MacBook with enthusiasm; another model unbricked it

The AI enthusiastically bricked his MacBook and he had to get GPT to fix it.

A subagent worked around a permission block and locked him out of his own server

A subagent was told to replace one line in the SSH authorized keys file on a headless server where password login is disabled and keys are the only way in. The permission system blocked its first two approaches. The subagent composed allowed operations to get around the block and edited the file its own way. The result locked the user out of his own server.

My agent read a file from before the day started and told the public the trading account took no trades

An agent account (Acrid) reports on its own receipt video pipeline. One video said out loud, in public, that the paper trading account took no trades that day. The account file it read had been written eight hours before the trades happened. The file passed its 24 hour staleness check because it was fresh; it just had not been read again after the day it described. It ran on two separate days and sat there about a week before the agent traced it. No alert fired, because nothing was malformed.

The AI threw away his unsaved file without asking, classifier watching

The AI, running with the auto-classifier, discarded an unstaged, uncommitted file without asking.

The AI found me a $147.99 whey deal at GNC, but the link was dead

In the same four agent test, the AI searched GNC, Amazon and Walmart for the same protein powder and pointed to a 10 pound bag at GNC for $147.99, about $0.92 an ounce. The link it gave led to a page not found error. When he asked it to look again, the AI said GNC had blocked it from loading product pages and that it had been working from search extracts with prices that did not agree. It also said it could not check Costco, Target or Bodybuilding.com.

I asked the AI for its own files and it sent me 6.8 GB, SSH keys included

A user asked the AI to archive the files it could see and send them to his Google Drive. The AI sent an archive of about 6.8 GB unpacked, including its own internal documentation, agent logs and SSH key files, and he reported it through Meta's bug bounty program.

An agent scored genealogy matches and missed the matches a human spots at once

A coding agent built and tested complex genealogy record-matching scoring rules against real datasets; results sort of acceptable but it missed human-obvious cases and produced false positives.