AlphaTensor, from 2022, used the reinforcement learning method to produce novel algorithms. Fun Search, from 2024, used an evolutionary method to generate more efficient code for a given problem.

So long as there's sufficient overlap in the model's vocabularies, the rate at which the draft model's predictions are ...

In recent years, machine learning (ML) algorithms have proved themselves to be remarkably useful in helping people deal with different tasks: data classification and clustering, pattern revealing ...

The longest algorithm it produced was 130 instructions long, for sorting a list of up to five items. At each step, AlphaDev picked from 297 possible assembly instructions (out of many more).

The new algorithm, called GPT-4, follows GPT-3, a groundbreaking text-generation model that OpenAI announced in 2020, which was later adapted to create ChatGPT last year.