Loading video...

Video Failed to Load

Go Home

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...

95,738 views • 1 year ago •via X (Twitter)

14 Comments

Google DeepMind's profile picture
Google DeepMind1 year ago

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. 🧵

Google DeepMind's profile picture
Google DeepMind1 year ago

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.

Google DeepMind's profile picture
Google DeepMind1 year ago

Over the past year, we’ve deployed algorithms discovered by AlphaEvolve across @Google’s computing ecosystem, including data centers, software and hardware. It’s been able to: 🔧 Optimize data center scheduling 🔧 Assist in hardware design 🔧 Enhance AI training and inference

Google DeepMind's profile picture
Google DeepMind1 year ago

We applied AlphaEvolve to a fundamental problem in computer science: discovering algorithms for matrix multiplication. It managed to identify multiple new algorithms. This significantly advances our previous model AlphaTensor, which AlphaEvolve outperforms using its better and more generalist approach. ↓

Google DeepMind's profile picture
Google DeepMind1 year ago

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 ↓

GC's profile picture
GC1 year ago

@kevinsekniqi does this count

Hashir Omer Farooqi's profile picture
Hashir Omer Farooqi1 year ago

*In 75% of cases, it rediscovered the best solution known so far.* If we don't have a proof that our best solutions are optimal, this 75% is a good evidence of memorization or training bias.

tumin~'s profile picture
tumin~1 year ago

I'm feeling insecure

Roman Leventov's profile picture
Roman Leventov1 year ago

This NotebookLM style is unbearable. Please don't use it for public posts like this

3THER_'s profile picture
3THER_1 year ago

Nice touch using notebookLM podcast for the explanation - I see what you did there ;D

Ciprianii's profile picture
Ciprianii1 year ago

applause

Achesui's profile picture
Achesui1 year ago

@grok explain this for a simple human being with low self-steem and with around 70 IQ, why is this important?

Oded Ben Dov 🧬's profile picture
Oded Ben Dov 🧬1 year ago

I need this for a missing piece of an P=NP proof. PLEASE

bry257's profile picture
bry2571 year ago

@gork holy shit look at this

Related Videos