|
‘Rogue’ AI Agents Will Kill Billions?
It was a rainy day when I met Bill Gates. That was in late 1999 at a Microsoft event in Seattle. We had a short chat about an aquisition. My impression was that he was a smart guy, but not very intelligent. Later that day he gave a talk. His PowerPoint presentation promptly blue-screened. He was embarrassed and helpless.
Gates knows a bit or two about how to profit from monopolizing software. Seen in that light his recent demand for regulation by claiming that AI could ’cause a billion deaths’ may even make sense:
In an interview with NBC Meet the Press, Gates said AI developers should be required to implement safeguards and monitoring systems, arguing that voluntary industry self-regulation is not enough.
“You need law enforcement and the politicians to get into the discussion about what safeguards and monitoring look like,” Gates told the outlet. “And that has to be a required thing.”
World to Gates: We already have laws that prohibit doing bad stuff. We also have law enforcement agencies. We have courts and judges that penalize people for doing bad things.
Killing a billion people is bad. It is prohibited for good reasons. Attempts to do so are criminal. People who try will go to jail.
To claim that AI could kill a billion people is like claiming that fire could kill a billion people. Of course it could. But no, it doesn’t.
After some unauthorized attempts to break into non-public databases and websites there has been embarrassing talk about ‘rogue AI agents‘.
There is no such thing as a ‘rogue’ AI agent. There is only deterministic software, written and launched by humans, that wraps around Large Language Models.
To understand how that works lets look inside:
An AI agent harness is the software infrastructure that wraps around a large language model (LLM) and enables it to act on tasks, not just respond to prompts. The model reasons through a problem and decides what to do next. The harness connects it to the tools, systems, memory and execution environments needed to carry out those actions.
Agent = Model + Harness
Think of the model as the “brain” that generates reasoning and decisions. The harness is everything around it that helps the agent operate safely and reliably, including:
- Tools: APIs, code execution, search, databases and business applications
- Memory: Prior context, user preferences and workflow history
- Workspace: Files, data, environments and systems the agent can access
- Guardrails: Permissions, policies, approvals and monitoring
Without a harness, a model can answer questions, but it can’t reliably run code, call APIs, access files, remember prior work or complete multi-step workflows on its own.
An AI agent, tasked with whatever, can and will only break into a website, if its harness (and the computer the ‘agent’ is running on) fails to stop it from doing so.
Whoever has programmed that harness (or miss-administrates the underlying system) is at least negligent in his duty. It is that person which is accountable for the agents misbehavior. It is that person which, where appropriate, should go to jail.
There is a very simple way for preventing AI agents from OpenAI or Anthropic from going ‘rogue’. Harshly penalize the CEOs of these companies, Sam Altman and Dario Amodei, each and every time their agents do.
AI systems do not think, feel, want or understand. They don’t go ‘rogue’.
biggerTo claim they do is silly.
Below are a some links that talk about AI Agents, Harnesses and Models. For the layman, this material might help provide some definitions and examples to help clarify what these systems do, what they’re composed of ( the functional components) and how the components relate / are combined to ” do AI”.
Some definitions before you hit the links:
LLM. A piece of software that ingests lots of information (documents, texts, etc) and can answer questions (relate bits of that information and speak it back in high-quality human language). Here’s more on LLMs.
Neural Network. (AI chatbot provided this answer): “A neural network is a machine learning model inspired by the structure of the human brain, consisting of interconnected nodes (or artificial neurons) that process data and learn patterns from it. They are widely used in various applications, including image recognition, natural language processing, and forecasting.”
Harness. Software that provides resources to the LLM, commands the LLM, stands between the LLM and the user, monitors the LLM’s behavior, manages LLM resources (memory, access to external systems, etc.) during execution/operation of the LLM.
Agent. An agent is the Harness + the Model (LLM). When you talk an “AI”, you’re talking to an Agent, and more specifically, you’re talking to the Harness component of the Agent.
VRAM. Special-purpose memory on a graphics card; this is the main workspace used by the Model. The CPU of that graphics card is a special-purpose graphics CPU designed to do graphics manipulation. Why graphics? Because the Model is expressed as a graph – a bunch of linked, related objects (a “neural network”), and graphics CPUs (“GPUs”) are optimal for manipulating such graphs.
Here’s more on GPUs:
GPUs run AI because neural networks are mostly enormous matrix multiplications, and a GPU performs thousands of those small calculations at once where a CPU does a handful. For language models the surprising bottleneck is memory, not math: how much VRAM a card has, and how fast it can move data, matters more than its raw compute.
MCP. (AI chatbot-provided answer): The Model Context Protocol (MCP) is an open standard introduced by Anthropic in November 2024 that standardizes how AI systems connect to external tools, data sources, and services through a universal interface. It acts like a “USB-C port for AI,” enabling AI assistants to securely access real-time data and perform actions beyond their static training knowledge.
Tom’s commentary: The MCP is a sub-component of the Harness. When AI agents “break out of the box”, the door they get through is probably contained within the MCP. Somebody didn’t do the MCP work thoroughly enough. All you AI experts, please comment on and refute that statement if necessary.
About those Harnesses
And now the links that describe how to make the Harness, connect it to a Model (LLM) and get yourself an AI chatbot (one type of AI Agent.
Anatomy of an Agent Harness. This has a lot of geek-speak, but should be fairly comprehensible for the layman.
Building an AI Agent Harness. More detailed, has some coding examples, and does a good job of describing the behind-the-scenes work that’s going on as you converse with your favorite AI chatbot. Still somewhat comprehensible by the layman; while it does provide some code examples, it explains in fairly plain English what the work is that the code is designed to do.
Posted by: Tom Pfotzer | Sep 30 2026 17:22 utc | 248
|
