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. 🧵

Excited to announce AlphaEvolve A powerful AI coding agent developed by our team in Google DeepMind that is able to discover impactful new algorithms for important problems in Maths and Computing by combining the creativity of large language models with automated evaluators.

After 1.5 years of work, I'm so excited to announce AlphaEvolve – our new LLM + evolution agent! Learn more in the blog post: deepmind.google/discover/blog/… White paper PDF: storage.googleapis.com/deepmind-media… (1/2)

We introduce 🌸✨ AlphaEvolve ✨🌸, an evolutionary coding agent using LLMs coupled with automatic evaluators, to tackle open scientific problems 🧑‍🔬 and optimize critical pieces of compute infra ⚙️ deepmind.google/discover/blog/…

Great job NV! We couldn't have made this happen without you

We're excited to introduce our new work on AlphaEvolve. Blog: deepmind.google/discover/blog/… Paper: storage.googleapis.com/deepmind-media…

AlphaEvolve, our new Gemini-powered coding agent, can help engineers + researchers discover new algorithms and optimizations for open math + computer science problems.  We’ve used it to improve the efficiency of our data centers (recovering 0.7% of our fleet-wide compute

AlphaEvolve uses LLMs to evolve new code to tackle a wide variety of problems. It's discovered improved solutions in pure mathematics, matrix multiplication, and computing infrastructure 💪

AlphaEvolve is here! 🧬 this is one special system (especially when optimising things with jagged edges 😊) -- had a fantastic time using it! congrats Alexander Novikov Matej Balog Ngân Vũ (NV) and team!! 🚀 you can register your interest in using it through the link below:

Announcing AlphaEvolve, our new LLM coding agent that has - made new scientific discoveries - discovered algorithms that are now deployed at Google (in Gemini, Transformers, TPU hardware design, and data centers) Blog: deepmind.google/discover/blog/… White paper: storage.googleapis.com/deepmind-media…

One of my favorite open problems is computing Kissing Numbers: how many unit spheres you can arrange touching a central unit sphere, in dimension d. Today, we published a paper showing an improvement in 11 dimensions. Using our new AI system, it took us just 2 days to find it./1

Google released AlphaEvolve. I'm trying to get a sense of whether the problems are hard to solve numerically. Let's focus on problem B.1. i'm going to do this live.

there are infinitely many other methods i could try. each requires careful debugging/tuning but i'm limited by my bandwidth and motivation and even with access to every LLM i failed. this is why having infinite compute + an LLM evolve your code wins. it doesn't have to care.

i built a visualization you can adjust the heights / see how hard it is to improve on google's or Matoslci-Vinuesa's solutions. link below.

🔥 Google DeepMind just dropped their "formal conjectures" project - formalizing statements of math's biggest unsolved mysteries in #LeanLang and #Mathlib! This Google-backed project is a HUGE step toward developing "a much richer dataset of formalized conjectures", valuable

So I've been messing around with this and LLMs. The quality of Mathlib + AI is getting to the point where mathematicians with *minimal* knowledge of Lean should be able to (with AI assistance) *state* (and themselves verify that the statement has the correct mathematical

Very excited to share that an advanced version of Gemini Deep Think is the first to have achieved gold-medal level in the International Mathematical Olympiad! 🏆, solving five out of six problems perfectly, as verified by the IMO organizers! It’s been a wild run to lead this

Official results are in - Gemini achieved gold-medal level in the International Mathematical Olympiad! 🏆 An advanced version was able to solve 5 out of 6 problems. Incredible progress - huge congrats to Thang Luong and the team! deepmind.google/discover/blog/…

Drastic progress on maths with Gemini 2.5! As a math undergrad, I am impressed 🤯 🥈 -> 🥇 ✅ Formal -> Informal ✅ Specialized model -> General model ✅ Available soon ✅ Huge thanks to IMO and congrats to all participants! Blog: deepmind.google/discover/blog/…