“Is AI a Silver Bullet? — Ian Cooper - Staccato Signals”
https://ian-cooper.writeas.com/is-ai-a-silver-bullet
> But the flaw in prompts as a description of the code to be generated tends to be that natural language is a remarkably poor medium for expressing the model that we want to use in our software. Every time we move away from a 3GL to create a more natural interface, we rapidly get diminishing ability to author software.
This entire essay is excellent
I will note that I’m much more sceptical than the author is of copilots. Most of the studies I’ve seen point to a very high error rate (security flaws, bugs, hallucinating APIs) in copilots, so the question is whether dev self-reports are accurate (studies lag reality) or not (devs are falling for confirmation and automation biases).
@baldur I can cosign this from personal experience. AI assisted code of any complexity; even as little as a four or five line function, tends to be thick with hidden flaws, of a kind a novice programmer might commit but an experienced programmer detects immediately on reading it.
I have almost never been able to save time by describing a function to an AI bot; the product it comes up with is very convincingly described, but it is quite easy to spot the inherent, trivially reproducible failure modes.
Predictive autocomplete can be a little bit handy, when it isn't just irritating. Actual AI code authorship is a waste of time -- when you in the end don't accept it -- and a catastrophe if you do.
