← Back to context Comment by measurablefunc 4 hours ago [flagged] 6 comments measurablefunc Reply dheera 4 hours ago "Most people" didn't figure this out either, the top 0.01% did. E-Reverance 4 hours ago I also wouldn't be surprised if they used AI to assist themselves in small ways measurablefunc 4 hours ago You're just moving the goal post & not addressing the question I asked. Why isn't AI optimizing the kernels in its own code the way people have been optimizing it like in the posted paper? aspenmartin 4 hours ago They do?https://www.deeplearning.ai/the-batch/alphatensor-for-faster...https://deepmind.google/blog/alphaevolve-a-gemini-powered-co...https://www.rubrik.com/blog/ai/25/teaching-ai-to-write-gpu-c... phkahler 4 hours ago It will, right after it reads the paper. 1 reply →
dheera 4 hours ago "Most people" didn't figure this out either, the top 0.01% did. E-Reverance 4 hours ago I also wouldn't be surprised if they used AI to assist themselves in small ways measurablefunc 4 hours ago You're just moving the goal post & not addressing the question I asked. Why isn't AI optimizing the kernels in its own code the way people have been optimizing it like in the posted paper? aspenmartin 4 hours ago They do?https://www.deeplearning.ai/the-batch/alphatensor-for-faster...https://deepmind.google/blog/alphaevolve-a-gemini-powered-co...https://www.rubrik.com/blog/ai/25/teaching-ai-to-write-gpu-c... phkahler 4 hours ago It will, right after it reads the paper. 1 reply →
E-Reverance 4 hours ago I also wouldn't be surprised if they used AI to assist themselves in small ways
measurablefunc 4 hours ago You're just moving the goal post & not addressing the question I asked. Why isn't AI optimizing the kernels in its own code the way people have been optimizing it like in the posted paper? aspenmartin 4 hours ago They do?https://www.deeplearning.ai/the-batch/alphatensor-for-faster...https://deepmind.google/blog/alphaevolve-a-gemini-powered-co...https://www.rubrik.com/blog/ai/25/teaching-ai-to-write-gpu-c... phkahler 4 hours ago It will, right after it reads the paper. 1 reply →
aspenmartin 4 hours ago They do?https://www.deeplearning.ai/the-batch/alphatensor-for-faster...https://deepmind.google/blog/alphaevolve-a-gemini-powered-co...https://www.rubrik.com/blog/ai/25/teaching-ai-to-write-gpu-c...
"Most people" didn't figure this out either, the top 0.01% did.
I also wouldn't be surprised if they used AI to assist themselves in small ways
You're just moving the goal post & not addressing the question I asked. Why isn't AI optimizing the kernels in its own code the way people have been optimizing it like in the posted paper?
They do?
https://www.deeplearning.ai/the-batch/alphatensor-for-faster...
https://deepmind.google/blog/alphaevolve-a-gemini-powered-co...
https://www.rubrik.com/blog/ai/25/teaching-ai-to-write-gpu-c...
It will, right after it reads the paper.
1 reply →