Phase 1: Self-Improving Systems · ~60 minutes · Python (stdlib · evolutionary-loop toy)

AlphaEvolve — Evolutionary Coding Agents

Pair a frontier coding model with an evolutionary loop and a machine-checkable evaluator.

Hiring signal: Can operate alphaevolve in production

Introduction

Let the loop run long enough. It discovers a 4x4 complex-matrix multiplication procedure that uses 48 scalar multiplications — the first improvement over Strassen in 56 years. It also finds a Google-wide Borg scheduling heuristic that recovers ~0.7% of cluster compute in production. The architecture is boring on purpose. The wins come from the evaluator's rigor.

Type: Learn Languages: Python (stdlib, evolutionary-loop toy) Prerequisites: Phase 15 · 01 (long-horizon framing), Phase 15 · 02 (self-taught reasoning) Time: ~60 minutes

Objective

Learning objectives

Unlock the full lesson

You've read the first 2 sections. The rest of this lesson covers The Problem, The Concept, Build, Check Yourself, Key Terms & Next — plus a hands-on lab, quiz, and project artifact.

Create a free account to unlock Phase 0 and Phase 1 of every course — no credit card.