🚀NEW COURSEVibe Coding AI Apps with Claude Code 🤖✨Enroll now
Reinforcement Learning · Code

AlphaDev

Free while signed in. Answers cite the passages they came from.

Paper preview
AlphaDev
The curator’s take

DeepMind's deep RL agent discovering faster sorting algorithms from scratch, now in LLVM.

Key points
01

Assembly-level discovery: Searches over CPU assembly instructions rather than high-level code, finding micro-optimizations humans would miss.

02

LLVM integration: Discovered sorting routines were integrated into the LLVM C++ standard library - the first major AI-discovered algorithm in production compiler infrastructure.

03

Human-beating benchmarks: Found 70% faster sorting for very small inputs and 1.7% faster for large inputs, running billions of times per day worldwide.

04

Algorithm discovery AI: A proof point for AI-driven algorithm discovery that would later be extended to matrix multiplication (AlphaEvolve) and other primitives.

Every Monday
Get next week’s papers.

The same picks and the same summaries, in your inbox. Free, and 176 issues deep.

Subscribe on Substack