Mastodawn

Very good points, a reply to a CEO who wondered why his engineers were resistant to using LLMs for coding:

@LillyHerself it's like...I know how I want to implement a feature within the technical constraints and subject matter context I'm working in.

Why would I sit down and try to explain in natural language my intentions and the surrounding constraints to a machine that has no concept of semantic knowledge?
Any response might be an ~alright first draft, but then I'd have to go in and converse my way to the solution I want, and in the end I'll have to manually edit stuff anyway.
THAT seems horribly inefficient.

If you wanna talk about reducing the time spent writing boilerplate code, look at languages like elixir with the phoenix framework.
You can generate boilerplate without stochastic wordpickers!

Show thread

Vincent Sparks

@wall_e @LillyHerself Exactly.

My dad is a pretty competent coder. He did it professionally for longer than I've been alive. He's worked in hardware design for a number of years now, but his coding skills are still fairly sharp. If I ask him for help solving a computer science problem, he's happy to give it to me, and he often has valuable insights -- but I find it often takes me twice as long to explain my problem to him than it would have to solve it on my own.

And he's a human. Why in the ever-loving sweet fuck would I do that with a machine that cannot synthesize solutions to novel problems at all and is pretty bad at synthesizing solutions to ones it's already seen?