Quoting Nelson Elhage
Feb 9, 2025
Great post from Nelson Elhage (Anthropic pre-training team) on adventures coding with Sonnet. Much of the post just describes the same journey that a lot of us are on at the moment (I’m still finding these posts fun to read, I wonder when the sense of wonder will be replaced by one of fatigue?), but there’s a couple of thoughtful nuggets towards the end that I’ve pulled out here:
You can now generate thousands of lines of code at a price of mere cents; but no human will understand them, and the LLMs are, for now, worse at debugging and refactoring and designing and maintaining those lines of code than they are at generating them. Thus, code is cheaper than ever, but I suspect that insight and good architectural design and understanding, at least for now, will become more valuable than ever.
I suspect this change also impacts which architectural patterns will make sense. Perhaps it will make it more important than ever to write code that is easy to delete, so you can just throw away whole modules and ask Claude N+1 or GPT M+1 to start over. Perhaps the bar to building “polyglot” systems, encompassing multiple different programming languages, will be much lower, if you’re able to harvest the benefits of different language ecosystems or performance characteristics, and don’t have to worry as much about hiring engineers comfortable in four esoteric languages. It’s gonna be interesting.