Hacker News Reader

A human deftly wielding an LLM can surpass that hurdle. I laugh at the idea of telling Claude Code to do the needful and then blindly pushing to prod.

This is not the right way to look at it. You don't have to have the LLMs directly coding your work unsupervised to see the enormous power that is there.

And besides, not all LLMs are the same when it comes to breaking existing functions. I've noticed that Claude 3.7 is far better at not breaking things that already work than whatever it is that comes with Cursor by default, for example.

Literally everything in this list, except AWS, introduces risk of breaking your code base without close oversight. Same people who copy paste LLM code into IDEs are yesterday’s copy paste from SO and random Google searches.