For a field aimed at creating artificial forms of intelligence, we spend way too little time looking at nature.
The creation of AI is one of the most profound technological challenges our species has ever faced. But we aren’t operating where no man has gone before… the whole point is that humanity already has. Nature has. The Universe has.
And as we say in Dutch: “Beter goed gejat dan slecht bedacht”, which translates to something like “Better stolen well than invented badly”.
My thesis is simple. The field of AI research is better off taking lessons from natural evolution than trying to reverse-engineer its way from scratch.
The reasoning behind it is simple too. The concept of evolution is universal. It appears in biology and the famous origin of species, but similarly in (astro)physics, economy, psychology, or any form of population dynamics.
Evolution is an iterative process that relies on two critical ingredients: natural selection and heritable variation. Their combined goal is to maximize evolutionary fitness, i.e. the contributions of an individual’s blueprint to successive generations.
In effect, evolution is a statistical hedge. Heritable variation ensures sufficient variety exists for some variant to be successful in a future generation, even if it is unclear what the requirements for success will be. And natural selection will make the decision. Evolution is the guaranteed optimization in the face of constantly changing conditions.
Evolution happens quite slowly in large mammals like humans or elephants, because generations take decades. But it is incredibly fast in bacteria (or even insects), because their generations are orders of magnitude shorter.
Evolution thrives on the rapidity of iteration.
Anyone working on AI should recognize that as a very familiar concept. After all, algorithms are the fastest-iterating mechanisms known. But to date, algorithms and AI have never embraced evolution to its full extent. We’ve applied natural selection principles in ensemble learning. But selection leads to a form of convergence, where after a while every model looks the same. How to enforce (heritable) variation in that context?
Nature’s answer is mutation. The probabilistic deviation from whatever natural selection converged on. Experimentation. In nature, a mutant is unlikely to survive. But sometimes, it hits the right note and gives birth to the future of its species.
At Allora Research, we have discovered that deliberate deviations from optimality across a swarm of agents systematically improve the performance of the swarm, relative to a swarm of optimized models.
We call this principle “Flawed in Nature, Perfect through Evolution”.
A single mutant is flawed and doomed to fail, but a swarm of uniquely different mutants maximizes its evolutionary fitness in the face of a constantly changing environment.
The needs of the many outweigh the needs of the few.
I believe the future of AI will be shaped by exactly this principle. We have spent so many resources on building the best individual models, but (as I’ve said many times) these are no better than interpolation machines. They replicate what they’ve learned, without shining the guiding light that human pioneers have.
Right now, we’re just hoping that AI will bring novelty. And while it can to a limited degree, it’s clearly missing something. A spark.
Originality, adaptability, creativity… all of these outshine AI slop any second. And the source of each of these qualities lies in mutation. The deliberate detuning of models away from the optimum.
That is what leads to intelligence. The ability to achieve your goals under any environment.
The missing ingredient in the race to AI has been exactly what the Flawed-in-Nature concept covers. And it was right in front of us, all that time. Because nature already mastered it.
Better stolen well than invented badly.
(Continue reading on our blog or on X.)
I’d love to hear other perspectives. Specific questions I’ve been thinking about:
1. I argued above that evolution is universal, appearing in biology, astrophysics, economics, psychology, and any form of population dynamics. In your own field, where have you seen variation-plus-selection produce outcomes that no amount of single-agent optimization could reach? I’d be interested in examples I haven’t encountered.
2. The paper models environmental drift as Poisson-driven impulses. In your work, what kinds of non-stationarity have you actually encountered? Sudden regime flips, slow drift, correlated shifts, seasonal cycles, adversarial changes? Which of these do you think the Flawed-in-Nature framing handles cleanly, and which might it struggle with?
3. Theorem 2 in the paper proves that any single model accumulates linear regret under unpredictable environmental change. The numerical experiments validate this for linear regression. Do you expect the result to hold for modern transformer-based LLMs in the same form, or is there something about scale, retrieval augmentation, or in-context learning that might change the story? What empirical test would convince you either way?
Thoughts are welcome.
