[dead]
AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
91–100 of 298 posts
Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
#92This is great.
But how incremental are these advancements?
I picked one at random (B.2 -- the second autocorrelation inequality). Then, I looked up the paper that produced the previous state of the art (https://arxiv.org/pdf/0907.1379). It turns out that the authors had themselves found the upper bound by performing a numerical search using "Mathematica 6" (p.4). Not only did the authors consider this as a secondary contribution (p.2), but they also argued that finding something better was very doable, but not worth the pain:
"We remark that all this could be done rigorously, but one needs to control the error arising from the discretization, and the sheer documentation of it is simply not worth the effort, in view of the minimal gain." (p.5)
So at least in this case it looks like the advancement produced by AlphaEvolve was quite incremental (still cool!).
Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
#93> Here, the code between >>>>>> REPLACE is the new segment that will replace the original one. This allows for targeted updates to specific parts of the code.
Anybody knows how they can guarantee uniqueness of searched snipped within code block or is it even possible?
Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
#94I'm surprised by how little detail is given about the evolution procedure:
>In AlphaEvolve, the evolutionary database implements an algorithm that is inspired by a combination of the MAP elites algorithm [71] and island-based population models [80, 94].
"inspired by" is doing a lot of heavy lifting in this sentence. How do you choose dimensions of variation to do MAP-elites? How do you combine these two algorithms? How loose is the inspiration? It feels like a lot of the secret sauce is in the answers to these questions, and we get a single paragraph on how the evolution procedure works, which is so vague as to tell us almost nothing.
Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
#95Earlier quoted context omitted.
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?
I have not read this linked article, but your comment made me recall a discussion about a speed up of CUDA kernels presented by Sakana AI Labs. The researcher Ravid Shwartz Ziv at NYU posted about it on LinkedIn [1], and here is the Twitter post of interest [2] """ Yesterday's news about Sakana AI Labs provided an important lesson for all of us working with AI agents. Their announcement of an AI system that could sup…
lmao this is exactly the kind of stuff I always see from Claude. It’s like adding a Skip() to a test and declaring it works now. “Well it’s a lot faster, I met the criteria of my TODOs cya”
I’ve seen it so much I kinda doubt it was “inadvertent” because they’re like seemingly intentional about their laziness, and will gaslight you about it too.
Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
#96The paper does not give that many details about the evolution part. Normally, evolutionary algorithms contain some cross-over component where solutions can breed with each other. Otherwise it's better classified as hill climbing / beam search.
I fear it’s not really evolutionary algorithms in the typical sense.
Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
#97Too bad the code isn't published. I would expect everything from DeepMind to be opensource, except model itself.
Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
#98Software engineering will be completely solved. Even systems like v0 are astounding in their ability to generate code, and are very primitive to whats coming. I get downvoted on HN for this opinion, but its truly going to happen. Any system that can produce code, test the code, and iterate if needed will eventually outperform humans. Add in the reinforcement learning, where they can run the code, and train the model…
"Coding" might be solved, but there is more to software engineering than just churning out code - i.e. what should we build? What are the requirements? Are they right? Whats the other dependencies we want to use - AWS or GCP for example? Why those and not others - whats the reason? How does this impact our users and how they use the system? What level of backwards/forwards compatibility do we want? How do we handle r…
Indeed, reasoning in the small and reasoning in the large are different skills. Architecture abstracts over code.
Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
#99Interesting to see Terence Tao in the authors list. I guess he's fully ai pilled now. Did he check the math results?
He is not in the author list, just acknowledged by the authors.
Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
#100Interestingly, it seems alphaevolve has already been in use for a year, and it is just now being publicly shown. The paper also mentions that it uses Gemini 2.0 (pro and flash), which creates a situation where Gemini 2.0 was used in a way to train Gemini 2.5.
I don't know if I would call this the fabled "self improving feedback loop", but it seems to have some degree of it. It also begs the question if Alphaevolve was being developed for a year, or has been in production for a year. By now it makes sense to hold back on sharing what AI research gems you have discovered.