Google DeepMind @GoogleDeepMind
Introducing AlphaEvolve: a Gemini-powered coding agent for algorithm discovery.
It’s able to:
Design faster matrix multiplication algorithms
Find new solutions to open math problems
Make data centers, chip design and AI training more efficient across @Google.
2025年05月15日 00:04 https://video.twimg.com/tweet_video/Gq6wlxiWQAAxqbO.mp4
Google DeepMind @GoogleDeepMind
Our system uses:
LLMs: To synthesize information about problems as well as previous attempts to solve them - and to propose new
versions of algorithms
Automated evaluation: To address the broad class of problems where progress can be clearly and systematically
measured.
Evolution: Iteratively improving the best algorithms found, and re-combining ideas from different solutions to
find even better ones.
2025年05月15日 00:04 https://pbs.twimg.com/media/Gq6wsomWgAA9wcI.jpg
Google DeepMind @GoogleDeepMind
Over the past year, we’ve deployed algorithms discovered by AlphaEvolve across @Google’s computing ecosystem,
including data centers, software and hardware.
Google DeepMind @GoogleDeepMind
We applied AlphaEvolve to a fundamental problem in computer science: discovering algorithms for matrix multipl
ication. It managed to identify multiple new algorithms.
Google DeepMind @GoogleDeepMind
We also applied AlphaEvolve to over 50 open problems in analysis , geometry , combinatorics and number theory
, including the kissing number problem.
In 75% of cases, it rediscovered the best solution known so far.
In 20% of cases, it improved upon the previously best known solutions, thus yielding new discoveries.
2025年05月15日 00:04
[動画] https://twitter.com/i/status/1922669334142271645
Google DeepMind @GoogleDeepMind
We’re excited to keep developing AlphaEvolve.
This system and its general approach has potential to impact material sciences, drug discovery, sustainability
and wider technological and business applications. Find out more ↓ https://goo.gle/3Fci8Ev
2025年05月15日 00:04
【引用ツイート】
Google DeepMind
Introducing AlphaEvolve: a Gemini-powered coding agent for algorithm discovery.
It’s able to:
Design faster matrix multiplication algorithms
Find new solutions to open math problems
Make data centers, chip design and AI training more efficient across @Google.