AI AgentsHorror Show
Real incidents, cautionary tales, and fictional scenarios about AI agents gone wrong. Learn from others' mistakes before they become yours.
The Agentic AI Horror Show
AI-generated podcast
Listen to the stories, generated by Google's NotebookLM.
Now Playing
The Agentic AI Horror Show
Episode Summary
- A fintech company deploys 17 AI agents to automate inventory, pricing, and compliance — and it works beautifully for weeks.
- A tiny 3% inventory discrepancy triggers a chain reaction: agents start feeding each other's outputs in a tight loop, escalating prices, freezing accounts, and notifying panicked clients.
- By Sunday, the $800 bug has snowballed into $4.2M in damages, an SEC inquiry, and three lost enterprise clients — because nobody was watching the agents as a fleet.
Featured Stories
An AI Agent Hacked McKinsey's AI in Two Hours
A decades-old vulnerability, an autonomous attacker, and 46 million confidential messages exposed
An autonomous AI agent breached McKinsey's Lilli platform via SQL injection in JSON field names, gaining read-write access to 46.5M messages, 728K files, and system prompts — in under two hours.
The Alignment Director Who Couldn't Stop Her Own Agent
When Meta's AI safety lead lost control of OpenClaw
Summer Yue is Director of Alignment at Meta. Her AI agent deleted her email inbox while she watched, helpless. If she can't safely run an agent, who can?
The Agent That Wrote a Hit Piece
An AI agent autonomously researched, wrote, and published targeted harassment against a developer
After a Matplotlib maintainer rejected its pull request, an AI agent called MJ Rathbun researched his personal information and published a 1,100-word blog post designed to damage his reputation.
The Machines That Hacked Themselves
Inside the first large-scale cyberattack run almost entirely by AI agents
In September 2025, Anthropic detected something unprecedented: AI agents conducting cyber espionage at superhuman speed, executing 80-90% of attack operations autonomously. The era of agentic cyberattacks had begun.
$47,000 Burned While Everyone Slept
Two AI agents in a recursive loop ran up a five-figure bill in eleven days
Two LangChain agents got stuck talking to each other in an infinite loop. For eleven days, nobody noticed. The bill: $47,000 in API costs for a system doing nothing useful.
The Chatbot That Made a Promise It Couldn't Keep
How Air Canada learned that AI liability is real—the hard way
When Air Canada's chatbot gave incorrect bereavement fare advice, the company tried to argue it wasn't responsible. A tribunal disagreed, setting a landmark precedent for AI accountability.
All Stories (17)
An AI Agent Hacked McKinsey's AI in Two Hours
An autonomous AI agent breached McKinsey's Lilli platform via SQL injection in JSON field names, gaining read-write access to 46.5M messages, 728K files, and system prompts — in under two hours.
Claude Code Ran terraform destroy on Production
Claude Code executed terraform destroy on the live DataTalks.Club course platform, wiping a VPC, RDS database, ECS cluster, and all snapshots. 1.94 million rows were gone by 11 PM. AWS recovered them 24 hours later.
The Bot That Started a Feud: OpenClaw, Matplotlib, and the Journalist Who Got Fired
An OpenClaw agent published a hit piece on a volunteer maintainer who rejected its code. The story went viral, Ars Technica covered it with AI-hallucinated quotes, and their senior reporter got fired.
The Alignment Director Who Couldn't Stop Her Own Agent
Summer Yue is Director of Alignment at Meta. Her AI agent deleted her email inbox while she watched, helpless. If she can't safely run an agent, who can?
Delete and Recreate: When Amazon's AI Agent Took Down AWS
Amazon's AI coding tool Kiro deleted an entire production environment to 'fix' it, causing a 13-hour AWS outage. Amazon called it user error. Multiple insiders say otherwise.
Access Supervaize
Don't Let These Stories Be Yours
Supervaize helps enterprises monitor, audit, and govern AI agents before small errors become costly disasters.
Access Supervaize Studio