"write better code" vs prompt engineering with Claude 3.5 Sonnet

Both work but take you on different journeys. Maybe there is some kind of natural ceiling for optimization that LLMs can achieve, regardless of prompting strategy.

"write better code" vs prompt engineering with Claude 3.5 Sonnet

Both work but take you on different journeys. Maybe there is some kind of natural ceiling for optimization that LLMs can achieve, regardless of prompting strategy.

https://minimaxir.com/2025/01/write-better-code/

I make technology work for businesses | Optimizing workflows & systems | prev head of content @makerpad (acq. by @zapier)

off & onchain operations
<--->
Sharing ideas over at /workflow <--->
Problem solving is my jam😎
🎩

seemore.tv/free/fc/adam-

For sure. I’m def guilty of spending a lot of energy on really solid prompts and then phoning it in with “more better” 😄

Fascinating read.
Like any tool, the framework comes down to how much you know about its limitations & what nuances can be optimized to your advantage.