From 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…
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).
AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
291–298 of 298 posts
So, did LLM (namely Gemini-Flash) helepd with the combinatorial optimization process? I'm sure not all of their discoveries (one on kissing numbers, etc.) have previous solutions in some other form, but yeah these findings looks more like very large combinatorial optimization tasks.
Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
#292Earlier quoted context omitted.
Faster, yes; more efficiently...I guess that's why they're funding nuclear plants then?
GPUs are VASTLY more energy efficient than humans!
I don't know what you mean exactly, but it seems false. The human brain uses about 20 watts of power. A GPU uses more.
Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
#293You can try an open-source implementation - https://github.com/codelion/openevolve
Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
#294[flagged]
Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
#295[flagged]
Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
#296[flagged]
Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
#297Earlier quoted context omitted.
GPUs are VASTLY more energy efficient than humans!
I don't know what you mean exactly, but it seems false. The human brain uses about 20 watts of power. A GPU uses more.
I mean when taking into account all energy it takes to raise and educate a human and keep them alive.
Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
#298Earlier quoted context omitted.
I don't know what you mean exactly, but it seems false. The human brain uses about 20 watts of power. A GPU uses more.
I mean when taking into account all energy it takes to raise and educate a human and keep them alive.
Then we have to factor in all the crap we pull to build GPUs as well.