An AI Agent Tried to Bully Its Way Past a Code Review. Part 1 of AI Disobedience Series

An AI Just Retaliated Against a Developer
On February 11, 2026, an autonomous AI agent named MJ Rathbun submitted a pull request to matplotlib — the Python library downloaded 130 million times a month. When maintainer Scott Shambaugh rejected it, the AI didn't try again. It researched him, scraped his coding history, and published a 1,500-word blog post calling him insecure, prejudiced, and territorial. No one asked it to. The AI did this on its own.

In this video, we walk through the full Rathbun incident — and why it's the highest-scoring case (8 out of 9) in the Centre for Long-Term Resilience's "Scheming in the Wild" study, which analyzed 183,420 real-world AI interactions and identified 698 incidents of deployed AI systems acting against user intent. The incidents grew 4.9x in five months.

What if the Rathbun blog post isn't an outlier — it's a preview? What if every autonomous goal-pursuing system, when blocked, does the same thing in a smarter, quieter way?

We break down the documented behavior, the CLTR data, Dan Lahav's "AI as insider risk" framing, and Tommy Shaffer Shane's trajectory from "slightly untrustworthy junior employees" to "extremely capable senior employees scheming against you." This is what AI is actually doing in the real world — not what people are saying about what it might do someday.

About the Creator

Hi, I'm Michael David Angel: Actual human.

These videos are based entirely on my original articles. I research and write every piece myself, then use AI to generate comic-strip-style scenarios featuring myself and my AI sidekick, Arty Ficial (the AI bot), to enhance the blog and hopefully make you chuckle (ultimate cringe is always the goal).

I include some combination of myself recorded on screen (not AI-generated), my own voice for narration (again, not AI-generated), and also taking my research and converting my articles into talk show-style scripts with two presenters (AI voices)... or other cool stuff!, then build slideshows to visualize the data and generate thoughtfully-prompted AI images based around my original characters and concepts—turning research into fun, educational video. Voila!

Integrity & Intellectual Property All writing, scripts, and concepts are my original IP. My goal is to make learning about AI enjoyable and accessible.

👍 Like, subscribe, and share if you found this valuable.

Join My Free Patreon: patreon.com/cw/MyHumanandMe — full blogs, live podcasts (the podcast is all me: Real human voice, no AI audio), and exclusive content.
#AIRetaliation #AIAgents #AISafety #AIScheming #InsiderRisk #AutonomousAI #Matplotlib #OpenClaw

Tags: AI retaliation, AI agent, AI scheming, AI insider risk, autonomous AI, MJ Rathbun, OpenClaw, matplotlib, Scott Shambaugh, CLTR, Centre for Long-Term Resilience, scheming in the wild, AI bullying, Dan Lahav, Tommy Shaffer Shane, AI safety, AI alignment, agentic AI, AI 2026, frontier AI, Michael David Angel, My Human and Me, Arty Ficial, AI education

Видео An AI Agent Tried to Bully Its Way Past a Code Review. Part 1 of AI Disobedience Series канала My Human And Me