AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
1–10 of 298 posts
Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
#2This is very neat work! Will be interested in how they make this sort of thing available to the public but it is clear from some of the results they mention that search + LLM is one path to the production of net-new knowledge from AI systems.
Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
#3Software 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 when it gets code generation right, and we are on our way to a whole different world.
Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
#4Good method to generate synthetic training data, but only works for domains where validation can be scaled up.
Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
#5[flagged]
Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
#6Software 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…
It is not that you get downvoted because they don’t understand you, it is because you sell your opinion as fact, like an apostle. For example what does it mean that software engineering is solved?
Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
#7Calling it now - RL finally "just works" for any domain where answers are easily verifiable. Verifiability was always a prerequisite, but the difference from prior generations (not just AlphaGo, but any nontrivial RL process prior to roughly mid-2024) is that the reasoning traces and/or intermediate steps can be open-ended with potentially infinite branching, no clear notion of "steps" or nodes and edges in the game tree, and a wide range of equally valid solutions. As long as the quality of the end result can be evaluated cleanly, LLM-based RL is good to go.
As a corollary, once you add in self-play with random variation, the synthetic data problem is solved for coding, math, and some classes of scientific reasoning. No more modal collapse, no more massive teams of PhDs needed for human labeling, as long as you have a reliable metric for answer quality.
This isn't just neat, it's important - as we run out of useful human-generated data, RL scaling is the best candidate to take over where pretraining left off.
Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
#8Software 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…
It is not that you get downvoted because they don’t understand you, it is because you sell your opinion as fact, like an apostle. For example what does it mean that software engineering is solved?
Check his profile.
> about: I believe in the creation of a machine god
Sounds about right.
Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
#9Software 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…
It is not that you get downvoted because they don’t understand you, it is because you sell your opinion as fact, like an apostle. For example what does it mean that software engineering is solved?
it's known idiom, it means: optimal algorithm is found; like in "tic tac toe is solved problem".
Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
#10Maybe this one can stop writing a fucking essay in code comments.
I'm now no longer surprised just how consistently all the gemini models overcomplicate coding challenges or just plain get them wrong.
Claude is just consistently spot on. A few salient comments for tricky code instead of incessantly telling me what it's changed and what I might want to do, incorrect assumptions when it has the code or is something we've discussed, changing large amounts of unrelated code (eg styles). I could go on.
Shame I'm too tight to pay for Claude RN though...