21–30 of 33 posts
there are more elegant ways to leverage an LLM, see AlphaEvolve: https://arxiv.org/abs/2506.13131
it's difficult to frame most coding tasks in such a way where you can trivially verify correctness.
what a nonsense, generated, article. > For context: GLM 5.1 ran the same task and reached 7.3x. Kimi K2.6 reached 5x. DeepSeek V4 Pro reached 3.3x. The models that stopped early did so because they issued no tool calls for five consecutive rounds, they concluded they couldn’t make further progress and stopped. Qwen3.7-Max didn’t stop. By this reasoning I could release a model that lacks all the basic optimisations. H…
Right now now I switched to the latest codewhale agent (in Rust), and it would perform much better according to his qualifications. Much better async IO implementation and orchestration, no more deadlocks as in the typical typescript tooling. It just doesnt stop out the blue, as claude, kimi or opencode.
I don't doubt that it did it but I wouldn't want to maintain whatever it ended up spewing after 35 hrs. In my experience, AI fixes problems by mostly adding more code. It's a short term gain for a long term hurt.
In my experience, AI fixes problems by mostly adding more code. In my experience, humans unfortunately tend to do the same.
Obligatory: Either written by AI or by a human who has spent so much time with AI that they adopted its writing style. Anyways. > Over 35 hours it performed 432 kernel evaluations. Each cycle meant writing code, compiling it, running it, reading the profiling output, deciding what to change, and trying again. The model diagnosed compilation failures it hadn’t seen before, identified performance bottlenecks through ru…
Genetic algorithm is random. This is intelligent evolution. Big difference.
Obligatory: Either written by AI or by a human who has spent so much time with AI that they adopted its writing style. Anyways. > Over 35 hours it performed 432 kernel evaluations. Each cycle meant writing code, compiling it, running it, reading the profiling output, deciding what to change, and trying again. The model diagnosed compilation failures it hadn’t seen before, identified performance bottlenecks through ru…
Genetic algorithm is random. This is intelligent evolution. Big difference.
Technically birdshot from a shotgun is also randomly distributed (passing through a cone). This actually improves the chance of hitting the clay pigeon, because the birdshot spreads out and each individual ball has a chance to hit.
Genetic algo is similar. it's an optimizer that - in order to avoid local optima - will 'shotgun' an area around its current best guess.
so basically just brute force the kernel. there are more elegant ways to leverage an LLM, see AlphaEvolve: https://arxiv.org/abs/2506.13131 it's difficult to frame most coding tasks in such a way where you can trivially verify correctness.
Obligatory: Either written by AI or by a human who has spent so much time with AI that they adopted its writing style. Anyways. > Over 35 hours it performed 432 kernel evaluations. Each cycle meant writing code, compiling it, running it, reading the profiling output, deciding what to change, and trying again. The model diagnosed compilation failures it hadn’t seen before, identified performance bottlenecks through ru…
Genetic algorithm is random. This is intelligent evolution. Big difference.
LLM written. See the authors twitter, he speaks english at a rather basic level and certainly did not write this https://x.com/mohitgeryani/with_replies
Earlier quoted context omitted.
Genetic algorithm is random. This is intelligent evolution. Big difference.
I got nerd-sniped wrt the genetic algorithm. Technically birdshot from a shotgun is also randomly distributed (passing through a cone). This actually improves the chance of hitting the clay pigeon, because the birdshot spreads out and each individual ball has a chance to hit. Genetic algo is similar. it's an optimizer that - in order to avoid local optima - will 'shotgun' an area around its current best guess.