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

Post by bossyTeacher » Thu, May 15, 2025, 10:14 AM UTC

starlust2 wrote: post #68

bossyTeacher wrote: post #27

Earlier 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?

The thing with vague requirements is that the real problem is that making decisions is hard. There are always tradeoffs and consequences. Rarely is there a truly clear and objective decision. In the end either you or the LLM are guessing what the best option is.

Post by amelius » Thu, May 15, 2025, 11:01 AM UTC

dymk wrote: post #208

antihipocrat wrote: post #184

Earlier quoted context omitted.

Is it new? I'm getting mixed messages from the posts here. On one side there is evidence that 48 and 46 multiplication solutions have been known (and could have found themselves in the model training data). On the other side I see excitement that the singularity is here. If the latter were the case surely we wouldn't be reading about it in a published paper, we would already know.

Let's assume that the 46 multiplication algorithm was known, prior to AlphaEvolve re-discovering it. AlphaEvolve still has made an improvement to a performance critical area that has had likely had thousands of engineer-hours put into it. None of those engineers apparently knew about the improved algorithm, or were able to implement the algorithm. This is empirical evidence of an LLM outperforming its (domain expert)…

Post by othorns » Thu, May 15, 2025, 11:34 AM UTC

schmidtleonard wrote: post #20

jasonjmcghee wrote: post #16

> 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.…

Remember that GPUs have cache hierarchies and matching block sizes to optimally hit those caches is a big win that you often don't get by default, just because the number of important kernels times important GPUs times effort to properly tune one is greater than what people are willing to do for others for free in open source. Not to mention kernel fusion and API boundaries that socially force suboptimal choices for…

Post by empath75 » Thu, May 15, 2025, 12:45 PM UTC

geodel wrote: post #210

Skylyz wrote: post #204

Earlier quoted context omitted.

And the invention of AGI will have the same impact as the electricity, i mean, they're both inventions, right ? I can't wait for all these billions of new full time jobs coming to replace the current ones. Farmers couldn't be replaced by low skill labor because they are low skill. Farmer didn't stop existing, but we went from 80% of the population farming is to 1-10%. If farming automation had happened in 1800 when 8…

Great points. Besides if one look around even today beyond people who somehow still succeeding at software hustle, there are already tons of people fallen off IT gravy train. A lot of manual testers who would make decent living are now eliminated by automation. Software document writers jobs are kind of gone. Developers are supposed to create document themselves on Confluent wiki etc. A lot of prized SAP consultants…

Post by gjm11 » Thu, May 15, 2025, 1:16 PM UTC

wbhart wrote: post #179

gjm11 wrote: post #172

Earlier quoted context omitted.

My understanding of the situation is that: 1. Waksman's algorithm works in any commutative ring admitting division by 2. 2. In particular, it won't work when the matrix entries are themselves matrices, which means you can't use it recursively to get an algorithm for n-by-n matrices with large n with a better exponent than you get from Strassen's algorithm. 3. The Deep Mind paper is annoyingly unexplicit about whether…

1. Correct 2. Correct, however you can use Waksman as a basecase and always beat Strassen (though it is not asymptotically better of course). 5. Possible, but even so, there is already an algorithm that will work with 46 real multiplications (and some divisions by 2). The real numbers are commutative and admit division by 2.