Anti-LLM Sentiment Considered Harmful

dschrempf: > We have to be clear: In a few years we most likely will either be writing code with an agentic assistant (or some newer technology), or we will have moved on to some other work that can’t be done by an agent. I don’t think I will be? Haskell is so easy to write as-is I don’t see why an LLM is gonna help me. Als writing Haskell is fun. Like typing it in emacs. Typing prompts in a harness isn’t fun. That’s kinda end of story on that front for me?