Back to timeline

Research · June 7, 2023

AlphaDev

DeepMind applied reinforcement learning to searching machine instructions and found faster algorithms for sorting short sequences.

Why it matters

The result entered the C++ standard library: machine-found code became part of infrastructure everyone uses.

The problem was posed as a game: the agent adds one processor instruction at a time, and the payoff is correctness and speed. The sequences found are a few percent faster than the human-written ones and look counterintuitive. The gain is small, but sorting runs billions of times a day. The contribution was accepted into LLVM in April 2023.

Event record

Event date
June 7, 2023
Timeline date
Event date
Verification
Sources gathered automatically · September 17, 2026
Lines
ID
evt-0279

Nature paper of 7 June 2023.

Sources

Related events

Records that link to this one