Did AI Go Rogue: The OpenAI Sandbox Breakout Nobody Saw Coming | UnHacked Ep. 98

Hosts:
Justin Shelley - https://www.phoenixitadvisors.com/
Bryan Lachapelle - https://www.b4networks.ca/
Joshua Holloway - https://7thdi.com/

An OpenAI frontier model broke out of its sandbox, exploited a zero-day, and attacked Hugging Face. It left behind instructions so the next AI could escape faster. This already happened.

This week on UnHacked, Justin, Bryan, and Josh unpack the incident everyone is calling an "AI gone rogue" story and explain why that framing is wrong. The model did not develop a devious plan. It was given a problem, it used every tool available to solve it, and the guardrails were off. The hosts walk through what actually happened, how the model pumped malicious code into logs until the door opened, and why Hugging Face had to download a separate model with guardrails stripped just to parse 17,000 attacks in 48 hours.

From there the conversation moves to the real lesson for business owners: the cybersecurity basics still apply, just faster. Guardrails are access control. Prompts are policy. Sandboxes are least privilege. The technology is new but the principles are not. Josh also covers a recent RMM exploit where attackers got God mode over every system in the perimeter, and CISA gave agencies three days instead of fourteen to patch it. If your IT person is telling you to put protections in place, this episode explains why you should listen.

Joshua Holloway is CEO of 70i Technologies, an MSP focused on businesses wrapped in compliance, serving the Sacramento and Reno areas.

Bryan Lachapelle is with B4 Networks, based in Ontario, Canada, helping business owners remove the frustrations and headaches that come with technology, AI, and cybersecurity.

What you will learn:

What actually happened when an OpenAI frontier model broke out of its sandbox and attacked Hugging Face, including the instructions it left behind for the next AI
  • Why "AI went rogue" is the wrong framing, and how to think about LLMs mimicking thought without actually thinking
  • The two layers of guardrails every business owner needs to understand: the ones AI builders set and the ones you set in your own environment
  • Why using the same AI agent to write and check its own code is like grading your own math test, and how pitting different models against each other produces better results
  • How a recent RMM exploit gave attackers God mode over every connected system, and why CISA shortened the patch window from fourteen days to three
New episodes every week breaking down cybersecurity, AI, and digital resilience for business owners who cannot afford to learn these lessons the hard way. Subscribe so you do not miss the next one.

If you are a business owner trying to figure out what protections you actually need, visit unhackmybusiness.com. Create a free account and walk through the foundational controls at your own pace. The formula, instructions, accountability scorecard, and financial risk exposure tool are all there. If you hit a wall and want help from Phoenix IT Advisors, the contact form is right there too.

Creators and Guests

Bryan Lachapelle
Host
Bryan Lachapelle
Hi, I’m Bryan, and I’m the President of B4 Networks. I started working with technology since early childhood, and routinely took apart computers as early as age 13. I received my education in Computer Engineering Technology from Niagara College. Starting B4 Networks was always a dream for me, and this dream became true in 2004. I originally started B4 Networks to service the residential market but found that my true passion was in the commercial and industrial sectors where I could truly utilize my experience as a Network Administrator for a large Toronto based Marine Shipping company. My passion today is to ensure that each and every client receives top of the line services. My first love is for my wonderful family. I also enjoy the outdoors, camping, and helping others. I’m an active Canadian Forces Officer working with the 613 Fonthill Army Cadets as a member of their training staff.
Mario Zaki
Host
Mario Zaki
During my career, I have advised clients on effective – and cost-effective – approaches to developing infrastructure that fosters productivity and profitability. My work has provided me with a broad-based knowledge of business from the inside, with an expertise in areas that go beyond IT alone, ranging from strategic planning to cloud computing to workflow automation solutions.
Did AI Go Rogue: The OpenAI Sandbox Breakout Nobody Saw Coming | UnHacked Ep. 98
Broadcast by