Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms

deepmind.google

Post reply on HN
Print view View original

271–280 of 298 posts

Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms

#271

Post by ActorNightly »

zaken wrote: post #73
moritonal wrote: post #25

For the people awaiting the singularity, lines like this written almost straight from science fiction: > By suggesting modifications in the standard language of chip designers, AlphaEvolve promotes a collaborative approach between AI and hardware engineers to accelerate the design of future specialized chips."

Honestly it's this line that did it for me: > AlphaEvolve enhanced the efficiency of Google's data centers, chip design and AI training processes — *including training the large language models underlying AlphaEvolve itself*. Singularity people have been talking for decades about AI improving itself better than humans could, and how that results in runaway compounding growth of superintelligence, and now it's here.

Long way to go Singularity. We don't even know if its possible.

Basically, singularity assumes that you can take the information about the real world "state", and compress it into some form, and predict the state change faster than reality happens. For a subset of the world, this is definitely possible. But for entire reality, it seems that there is a whole bunch of processes that are computationally irreducible, so an AI would never be able to "stay ahead" or so to to speak. There is also the thing about computational ir-reversibility - for example observing a human behavior is seeing the output of a one way hashing function of neural process in our brain that hides a lot of detail and doesn't let you predict it accurately in all cases.

Also, optimization algorithms are nothing new. Even before AI, you could run genetic algorithm or PSO on code, and given enough compute it would optimize the algorithm, including itself. The hard part that nobody has solved this is abstracting this to a low enough level to where its applicable across multiple layers that correspond to any task.

For example, let say you have a model (or rather an algorithm) that has only a single interface, and that is the ability to send ethernet packets, and it hasn't been trained on any real world data at all. If you task it with building you a website that makes money, the same algorithm that iterates over figuring out how to send IP packets then TCP packets then HTTP packets should also be able to figure out what the modern world wide web looks like and what concepts like website and money is, building its knowledge graph and searching on it and interpolating on it to figure out how to solve the problem.

Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms

#272

Post by aseg »

nickpsecurity wrote: post #201
aseg wrote: post #136

Finally—something directly relevant to my research ( https://trishullab.github.io/lasr-web/ ). Below are my take‑aways from the blog post, plus a little “reading between the lines.” - One lesson DeepMind drew from AlphaCode, AlphaTensor, and AlphaChip is that large‑scale pre‑training, combined with carefully chosen inductive biases, enables models to solve specialized problems at—or above—human performance. - These s…

Non-expert here who likes reading lots of this kind of research. I have a few questions. 1. Why does it need a zeroth order optimizer? 2. Most GA's I've seen use thousands of solutions. Sometimes ten thousand or more. What leads you to use 60,000 calls per iteration? 3. How do you use populations and "islands?" I never studied using islands. 4. You said the smaller models are often better for "shorter" code. That mak…

Happy to answer them!

1. Because we only have blackbox access to the LLM and the evaluation function might not be differentiable.

2. We're trying to search over the space of all programs in a programming language. To cover enough of this huge search space, we need to instantiate (1) a large number of programs in each population and (2) a large number of populations themselves (3) A large number of update steps for each population.

3. I have a couple of graphics motivating, conceptually, what an island/population looks like: https://trishullab.github.io/lasr-web/ . This whitesheet might also be useful: https://arxiv.org/abs/2305.01582

4. This is an interesting question. I believe so. However, my observations were derived from a non turing complete language (mathematical equations). There might be other ways of enforcing a succinctness pressure.

Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms

#273

Post by aseg »

knowaveragejoe wrote: post #216
aseg wrote: post #136

Finally—something directly relevant to my research ( https://trishullab.github.io/lasr-web/ ). Below are my take‑aways from the blog post, plus a little “reading between the lines.” - One lesson DeepMind drew from AlphaCode, AlphaTensor, and AlphaChip is that large‑scale pre‑training, combined with carefully chosen inductive biases, enables models to solve specialized problems at—or above—human performance. - These s…

> The “knowledge retrieval” stage may hallucinate, but—because the knowledge is expressed as code—we can execute it and validate the result against a custom evaluation function. Can you give a concrete example of this? It's hard for me to conceptualize.

Assume you have data for Hooke's law (a spreadsheet with F, x, and other variables) and you want AlphaEvolve to give you the equation ``F = -C_1*x``.

Let's say the model hallucinates in two directions:

1. "There is a trigonometric relationship between variable F and x". It expresses this as ``F = -C_1*sin(x)``. You fit the constant C_1 w.r.t the dataset, execute the program, and your best fit has a high error. You can discard the program.

2. "There is an inverse linear relationship between variable F and x". Now it expresses this as ``F = -C_1*x``. You fit the constant C_1 w.r.t the dataset, execute the program, and your best fit has extremely low error. You now know for sure that you're on the right track.

Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms

#276

Post by hariseldom »

Imnimo wrote: post #94

I'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? H…

https://arxiv.org/pdf/2501.09891v1 from deepmind in January goes into the evolutionary algorithm a bit - no math though.

Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms

#279

Post by thatguysaguy »

lionkor wrote: post #233
thatguysaguy wrote: post #202

Earlier quoted context omitted.

Are you claiming that for the open problems they give record-breaking solutions for, there were just answers on the web waiting to be found?

No, I'm saying they have a massive database of solutions (the training set) and don't even bother proving that their solution isn't in there. I'm not claiming something, they are failing to provide some necessary information here

Many of the problems (such as the matmul and packing problems) have existing "scoreboards". It would be quite surprising if so many records had already been broken without it coming to the attention of the people who care about the problem.

Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms

#280

Post by alexnovikov »

Zr01 wrote: post #240
aabajian wrote: post #63

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…

A complex multiplication is "worth" at least 3 real multiplications.

Fair point! A single complex multiplication `(a+bi)(c+di)` indeed requires at least 3 real multiplications to be implemented.

However, when researchers (and systems like AlphaEvolve in this context) analyze fast matrix multiplication algorithms like Strassen's, the primary goal is usually to improve the asymptotic complexity (and understand the space of these algorithms better). This complexity is determined by the number of multiplications in the field over which the matrices are defined. * For real matrices, we count real scalar multiplications. * For complex-valued matrices (as in the 4x4 example where AlphaEvolve found a solution with 48 scalar multiplications), "scalar multiplication" refers to a complex scalar multiplication.

The key is that these are the operations you recurse on. Additions, or the constant factor cost of implementing one field's multiplication, don't change the exponent in the `N^(log_base(multiplications))` complexity. They are constant factors.

Of course, for practical performance on a specific 4x4 matrix, one would absolutely dive into the real operations, additions, memory layout, etc., but making 4x4 matrix multiplication practically faster on some particular hardware was not the focus in this section. (We do improve practical implementation of large matrix multiplications on the target hardware in the “Enhancing AI training and inference” section of the blog post.)

(Disclaimer: one of the authors.)

Post reply on HN