what do you think of jonathan blow's takes on this stuff?
LLMs will never be capable of making real good software
because they're not like alphazero, they just spit words
once someone does an AI t...
> because they're not like alphazero, they just spit words
This seems to be changing right now: here's a paper on recent, roughly speaking, AlphaZero-like research that specifically uses coding problems. They make it learning on experience rather than on traditional datasets.
https://arxiv.org/abs/2505.03335
This seems to be changing right now: here's a paper on recent, roughly speaking, AlphaZero-like research that specifically uses coding problems. They make it learning on experience rather than on traditional datasets.
https://arxiv.org/abs/2505.03335