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!

@wall_e Only the C-suite is being taken in by this, because they often/usually don't understand the process of coding.

@LillyHerself I bet there's still enough C-Suite out there that have a KPI like: lines of code per engineer per time unit.

And yeah, AI can probably be used to optimize for that kind of metric