Post

At the risk of starting the flame war to end all flame wars... Modern LLMs (GPT-5.1, Claude 4.5, Gemini 3) produce excellent code and can be a significant productivity boost to software engineers who take the time to learn how to effectively apply them - especially if used with coding agent tools

They can be useful for developers who are experts and know what the output should be. They are a hindrance to junior developers and you shouldn't use them if you are learning or you don't know how to evaluate the output.

Which is to say, the opposite is: - exposure to things they may not have otherwise explored - used as an opportunity to learn more and introspect, not just poop out code - opportunity to learn more about the craft through the combination of those two thigns