Why Gemini(s)? Why not LLMs fine tuned for LARPing as a researcher?
AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
241–250 of 298 posts
Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
#242> AlphaEvolve achieved up to a 32.5% speedup for the FlashAttention kernel implementation in Transformer-based AI models > In roughly 75% of cases, it rediscovered state-of-the-art solutions, to the best of our knowledge. > And in 20% of cases, AlphaEvolve improved the previously best known solutions These sound like incredible results. I'd be curious what kind of improvements were made / what the improvements were.…
I'm thinking reading numbers like this is really just slop lately. FA achieving a 32.5% speed up? Cool. Why not submit it as a PR to the Flash Attention repo then? Can I read about it more in detail?
Exactly, as a great dev once said: "talk is cheap, show me the code"
Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
#243From the paper, "Notably, for multiplying two 4 × 4 matrices, applying the algorithm of Strassen recursively results in an algorithm with 49 multiplications, which works over any field...AlphaEvolve is the first method to find an algorithm to multiply two 4 × 4 complex-valued matrices using 48 multiplications." If you do naive matrix multiplication, you get a sense that you're doing similar work multiple times, but i…
Are you sure the saving needs complex values? I think their algorithm works over any char 0 field. Probably needs to just divide by some divisor of 4!=24 if I had to guess.
Their decomposition of the (4,4,4) matrix multiplication tensor is explicitly listed in their Colab notebook, and it contains complex numbers.
Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
#244From the paper, "Notably, for multiplying two 4 × 4 matrices, applying the algorithm of Strassen recursively results in an algorithm with 49 multiplications, which works over any field...AlphaEvolve is the first method to find an algorithm to multiply two 4 × 4 complex-valued matrices using 48 multiplications." If you do naive matrix multiplication, you get a sense that you're doing similar work multiple times, but i…
>What I find interesting is that it seems the extra savings requires complex values. There must be something going on in the complex plane that is again over-counting with the naive approach.
"The rank of a tensor depends on the field over which the tensor is decomposed. It is known that some real tensors may admit a complex decomposition whose rank is strictly less than the rank of a real decomposition of the same tensor."
https://en.wikipedia.org/wiki/Tensor_rank_decomposition#Fiel...
Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
#245anyone else feel out-evolved yet?
Not really, only when looking back at the 60's and 70's when most of the important algorithms I use were invented. For example, LR parsing and A*. Just wait until the MBA's and politicians learn about this Adam Smith guy. A pipedream now, but maybe in the future schools will be inspired to teach about dialectical reasoning and rediscover Socrates. [end of snark] Sorry, I'm getting tired of ad-fueled corporations tryi…
This is one of the most valuable intellectual skill that humans can develop and is even more relevant in a world where manipulation and misinformation at scale is effectively commoditized. Like you, I'm not going to outsource it to a corpo, and will use LLMs as simply another source to be used critically in learning and/or reaching a decision.
Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
#246Earlier quoted context omitted.
They address this in the AlphaEvolve paper: "While AI Co-Scientist represents scientific hypotheses and their evaluation criteria in natural language, AlphaEvolve focuses on evolving code, and directs evolution using programmatic evaluation functions. This choice enables us to substantially sidestep LLM hallucinations, which allows AlphaEvolve to carry on the evolution process for a large number of time steps."
It is interesting how google turned the tide on GenAI race, and seems to be leading the pack, with not only great fundamental research, but also interesting model and products. To what extent these remain a niche/nice to have or become a sensation remains to be seen, but I hope if they don't reach hype status, they might be released to the open weights world.
> It is interesting how google turned the tide on GenAI race, and seems to be leading the pack
I think this is perhaps due to Google combining Google Brain and DeepMind, and putting Demis Hassabis at the helm?
I agree, Google is very much leading the pack in AI now. My worry is that they have mentioned recently that they are less inclined to release research into the open if they think it will give their competition a step-up. Demis is more scientist than business-man, so perhaps there's hope that he will be willing to continue to release research.
Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
#247This is an important moment. We now have verifiable evidence that these systems can do new useful research that has actual value in the real world. That 1% savings is only the start as well. I would expect the compounding number of gains to be significant over some time. Also in a way this process was used to make gemini 2.5 pro better, so its like a baby step towards recursive self improvement. Not fully automated y…
It's always "revolutionizing our internal workflows" or "30% of code at Microsoft is AI now" but never improving a codebase you can actually see
Making a significant improvement to the state of the art of one particular algorithm is one thing, but I've seen new tools do that since the 80s
I'll be convinced when LLMs start making valuable pull requests, non-obvious corner cases or non-trivial bugs in mature FOSS projects
Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
#248Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
#249Earlier quoted context omitted.
By googling "4x4 matrices multiplication 48" I ended up on this discussion on math.stackexchange https://math.stackexchange.com/questions/578342/number-of-el... , where in 2019 someone stated "It is possible to multiply two 4×4 matrix A,B with only 48 multiplications.", with a link to a PhD thesis. This might mean that the result was already known (I still have to check the outline of the algorithm).
From some conversations on Twitter, it seems plausible that the rank-48 decomposition of the 4×4 matrix multiplication tensor really is new; and that perhaps where things have gone awry is attempting to summarise this result in a more lay-friendly manner: the algorithm in that post apparently doesn't constitute or imply a rank-48 tensor decomposition. On the other side, it's claimed here that an algorithm that uses o…
Ironically their AI can cite the relevant paper with 46 steps if asked: https://gemini.google.com/share/b0d5d6a76c87
Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
#250Earlier quoted context omitted.
What about brownfield development though? What about vague requirements or cases with multiple potential paths or cases where some technical choices might have important business consequences that shareholders might need to know about? Can we please stop pretending that software engineering happens in a vacuum?
> What about vague requirements or cases with multiple potential paths or cases where some technical choices might have important business consequences that shareholders might need to know about? If the cost of developing the software is 0, you can just build both.
or you can build 20 different versions. Your non technical person won't be happy about this though. They wanted 1 software system not 20 nor 2. Just one