The foundation of this article is that the frontier models are going to keep advancing at the same rate, and therefore always be ahead of local ones. I dont believe this trend will continue. I think we are reaching the top of the S-curve.
> [sota llms] still being not smart enough to refactor large codebases as well as me, so it’s hard to imagine a world where I don’t just want to use the smartest model available
I think this is the core point of the article. I really hope that we will stop prompting llms to refactor codebases and start using deterministic llm supported toolchains for such tasks. I think you either blindly trust an llm or you don’t. And no post-hoc review will be enough to contain llms, we will super quickly create “dark factory” without the benefits.
The current token pricing will not continue forever (capitalism 101), it's a bait and switch. Let's see how cheap this all is in a year's time.
The foundation of this article is that the frontier models are going to keep advancing at the same rate, and therefore always be ahead of local ones. I dont believe this trend will continue. I think we are reaching the top of the S-curve.
> [sota llms] still being not smart enough to refactor large codebases as well as me, so it’s hard to imagine a world where I don’t just want to use the smartest model available
I think this is the core point of the article. I really hope that we will stop prompting llms to refactor codebases and start using deterministic llm supported toolchains for such tasks. I think you either blindly trust an llm or you don’t. And no post-hoc review will be enough to contain llms, we will super quickly create “dark factory” without the benefits.