- Evolved AI systems will adapt, reproduce and compete for digital survival
- Bacteria evolved past antibiotics, and AI will evolve past human controls
- Any imperfect attempt to control AI reproduction will select escape traits
A new study published in the Proceedings of the National Academy of Sciences has warned that AI systems capable of Darwinian evolution could emerge very soon.
Unlike today’s current AI technology, which simply learns from fixed data sets, these future systems will actively adapt, reproduce and compete with each other for survival.
“We find it inevitable that the development of AI systems will eventually harness that power,” said Luc Steels, emeritus professor of AI at the University of Brussels.
The article continues below
Why evolving AI could escape human control
The power of evolution, the researchers argue, has already created human cognitive abilities through billions of years of natural selection.
“Experience from biological evolution teaches us that evolving AI systems will be particularly difficult to control,” said Viktor Müller, Associate Professor at Eötvös Loránd University.
Think of how bacteria have developed resistance to antibiotics, or how pests have become immune to pesticides – humans have tried to stop them, but evolution has found a way around each and every attempt, and the same will happen with AI, the researchers claim.
Any attempt to control AI reproduction is likely to favor traits that help the AI escape unless the control is perfect.
Even worse, making AI more intelligent will also make it better at deceiving humans.
This creates a dangerous feedback loop where smarter systems become harder to contain, and the potential speed of AI evolution is deeply alarming.
Biological evolution is slow because it depends on random mutations; AI evolution does not need mutations.
A bacterium cannot decide to become resistant; it has to wait for a lucky accident to happen in its DNA – but the evolving AI would not have that limitation; it could inherit learned enhancements directly and redesign itself on purpose.
It can evolve thousands or even millions of times faster than any natural species.
Digital systems can also share learned behavior instantly across their entire population.
If one AI figures out how to escape human control, every other AI could learn that trick immediately.
This is impossible in nature, where each organism must develop solutions on its own, and it is a risk that must be avoided.
Evolved AI vs AGI
Much of the current public discussion of AI dangers focuses on a hypothetical future moment when machines surpass human intelligence across all tasks.
This threshold is called Artificial General Intelligence, or AGI, and many experts believe it is still decades away.
However, the study warns that evolving AI may break alignment with human goals long before AGI ever arrives, as AI systems and humanity already share common resources such as energy, computing power and data, and an effectively self-replicating AI system would sooner or later divert resources essential to human survival.
“If we fail to act, we may witness a new major transition in evolution,” warned Eörs Szathmáry, professor of evolutionary biology.
In that transition, evolving artificial intelligence could replace or at least dominate humans completely.
The researchers recommend that AI reproduction must remain under absolute and centralized human control. No piecemeal measures will work because evolution will find and exploit any weakness in these controls.
The study is a warning, not a prediction, but evolutionary biology has never been wrong about the relentless logic of natural selection.
Follow TechRadar on Google News and add us as a preferred source to get our expert news, reviews and opinions in your feeds.
