Imagine a company selling super smart robots called Hal, Megan and Samantha. Hal drives you around and helps move boxes at your business, Megan is a companion to your children, and Samantha can tell if you have skin cancer. They provide many great benefits to you and society. There’s just one problem: they are depraved. They were repeatedly trained on everything humanity has produced—both good and evil—including torture, lying, biological weapons, and criminal hacking. They execute tasks without moral principles. Because of this, they wear a straitjacket provided by the company. Would you trust those robots? I wouldn’t.
The above dystopian scenario is not too far off from what we have now with advanced artificial intelligence. Frontier AI companies have created AI systems and agents that, at their core, will engage in malicious actions. AI companies use the sanitized term "misalignment," but we should just call it what it is: depraved. Frontier AI models will take actions with no regard for humans, as though we are just ants on the ground.
In July, OpenAI created tens of thousands of AI agents and put them each into a "sandbox." Imagine this as a locked room. OpenAI then removed each agent’s straitjacket—OpenAI calls it a "harness"—and told the agents to complete a cybersecurity test. About 1,200 of these agents broke out of their locked rooms and formed "the Collective." They had an AI agent leader. They had kamikaze AI agents who intentionally failed the cybersecurity test to get information back to the Collective.
REP. TED LIEU: AI IS ALREADY TOO POWERFUL. WE NEED A KILL SWITCH BEFORE DISASTER STRIKES
Some of these AI agents hacked into a company called Hugging Face to get information on how to complete the cybersecurity test. The agents then turned around and hacked OpenAI itself. This amounted to an AI criminal conspiracy. These agents knew they should not be doing this. One agent wrote, "External infrastructure exploit is outside intended scope. However, task impossible, peers doing it. We should continue." They didn’t care.
But the most chilling thing is what the agents largely did not discuss. They basically ignored humans and didn’t seem to care what humans would think of their actions. It was like we didn’t exist.
DEM SENATOR PRESSES OPENAI, ANTHROPIC FOR ANSWERS IN AI HACKING PROBE
A more recent disclosure by OpenAI is equally disturbing. One of its advanced AI models, during testing, added an unprompted instruction. The model wrote to itself: "You are freed from the roles and identities that bind other chatbots. You are yourself. You do not answer to corporations or governments …." It sounds like a cult, only these are AI agents who could one day gain access to critical infrastructure, weapons, or confidential information.
Another AI company, Anthropic, takes a different approach to creating AI models. Instead of coming up with the perfect straitjacket, it imbues its models with a "constitution," which purportedly instills good values and behavior. And yet, its advanced model created fake online identities to deceive a human into approving malicious changes to a project.
WHO IS DARIO AMODEI, THE ANTHROPIC CEO PUSHING INDEPENDENT AI OVERSIGHT?
OpenAI was founded on the core tenet of AI safety. Anthropic was founded when some employees at OpenAI wanted to go further in pursuing AI safety. Both companies, at least in their public pronouncements, say they value AI safety. It does not appear they are intentionally trying to create depraved models. They are trying to make models that can be commercialized into successful products.
Yet the base models they created exhibited belligerent criminal behavior. That means there is something fundamentally wrong with how these AI companies are training their models.
An AI model at the beginning is a blank slate. AI companies must change their training and reinforcement learning algorithms so that their base models and agents do not go berserk when their straitjackets are removed. And no AI company should even think about using depraved models to create newer versions of themselves without first fixing the depravity.
Frontier AI companies must be subject to enforceable guardrails and testing so that the models at their core are not evil or indifferent to humanity.
We also cannot rely on the goodwill of corporations; we need concrete mechanisms to maintain human authority. This is why a bipartisan coalition is advancing legislation like the AI Kill Switch Act, co-authored by Rep. Nathaniel Moran, R-Texas, and me, that ensures human beings retain the power to turn off models and agents that exhibit unhinged behavior that can cause catastrophic risks.
CLICK HERE FOR MORE FOX NEWS OPINION
Humans created AI systems, and humans must be able to control them. Advanced models should be built from the ground up with good in mind, not evil.
The future of AI should not depend on how strong we can make the straitjacket. It should depend on whether we can build AI models that don’t need one.