Python was built around human limitations. AI agents don't have those limitations, so Python's trade-offs (loose typing, runtime errors, no compiler) are now liabilities. Rust's strict compiler, which humans hate, doesn't bother agents at all. Pick your language based on who's actually writing the code.
I agree with the general insight here. Python is great for humans but once they are out of the loop it's no longer as useful. Having a compiler is more useful for LLMs indeed.
However we are moving one step closer to complete inability for humans to understand the code, as there are likely 100x more developers with experience in Python than Rust. If humans are indeed going to be the bottleneck then perhaps this is inevitable, and languages fitted especially for LLMs will dominate.
I’ve been using rust for vibecoding too for similar reasons.
Do enough of it though and you definitely notice the huge difference in training data available. Python converges on a working solution noticeably faster especially for things like APIs and LLM stuff.
So these days I’m making a judgement call at the start on which language is the better tradeoff. Generally rust for raw data processing and Python for website backend APIish tasks
4 comments
[ 3.1 ms ] story [ 26.4 ms ] threadHowever we are moving one step closer to complete inability for humans to understand the code, as there are likely 100x more developers with experience in Python than Rust. If humans are indeed going to be the bottleneck then perhaps this is inevitable, and languages fitted especially for LLMs will dominate.
Do enough of it though and you definitely notice the huge difference in training data available. Python converges on a working solution noticeably faster especially for things like APIs and LLM stuff.
So these days I’m making a judgement call at the start on which language is the better tradeoff. Generally rust for raw data processing and Python for website backend APIish tasks