ATG🧬Cƒ🌿
🧬

Can algorithms evolve?

Darwinian AI

Pint of Science 2026 · A tour through ChatGPT, evolutionary algorithms, and a PhD thesis that ties them together to evolve RISC-V chips that align DNA.

Interactive slidesMay 18, 2026Alejandro Fernández Camello

It is not the strongest species that survives, but the one that best adapts. — Charles Darwin, 1859

prompt:

El gato subió al

  • tejado62%
  • árbol18%
  • sofá11%
  • muro6%
  • coche3%

Next-token prediction

Given a prefix, the model assigns a probability to every candidate word and picks one. That is all — and yet, everything.

generation:0/18
fitness:0.00
Evolving...

Evolutionary loop

A population converges toward the solution after repeating crossover, mutation, fitness and selection. Fitness rises, spread shrinks.

The journey

Three ideas and a closer. From predicting the next word to evolving programs guided by an LLM.

💬
01

ChatGPT, in one line

A machine trained on almost all of the internet to do one thing: guess which word comes next. The newer models also think out loud before answering.

🧬
02

Evolutionary algorithms

We copy nature’s recipe. Random population → crossover and mutation → fitness → selection. Repeat until a solution is good enough.

🔬
03

My research

We evolve RISC-V — an open chip — to align DNA sequences. The population is programs; the LLM plays the role of crossover and mutation, proposing meaningful changes.

04

Yes, they can evolve

When a language model guides the evolutionary loop, algorithms evolve faster and further than ever. Open hardware, evolved software, cheaper biology.

🧬

View the presentation

Interactive HTML slides — open directly in your browser.