11–20 of 460 posts
Earlier quoted context omitted.
Have you tried describing to Claude what it is? The more the detail the better the result. At some point it does become easier to just do it yourself.
Most people just forget to tell it "make it quick" and "make no mistake"
Most humans also write plausible code.
Enterprise customers don't buy correct code, they buy plausible code.
I tried to make Claude Code, Sonnet 4.6, write a program that draws a fleur-de-lis. No exaggeration it floundered for an hour before it started to look right. It's really not good at tasks it has not seen before.
LLMs are really bad at anything visual, as demonstrated by pelicans riding bicycles, or Claude Plays Pokémon. Opus would probably do better though.
Enterprise customers don't buy correct code, they buy plausible code.
I tried to make Claude Code, Sonnet 4.6, write a program that draws a fleur-de-lis. No exaggeration it floundered for an hour before it started to look right. It's really not good at tasks it has not seen before.
Given a harness that allows the model to validate the result of its program visually, and given the models are capable of using this harness to self correct (which isn't yet consistently true), then you're in a situation where in that hour you are free to do some other work.
A dishwasher might take 3 hours to do for what a human could do in 30 minutes, but they're still very useful because the machine's labor is cheaper than human labor.