Why LLMs can't really build software(zed.dev)
321 points by srid | 196 comments
A Zed blog post by Conrad Irwin arguing that LLMs cannot really build software, drawing on his experience of what effective software engineers do.
321 points by srid | 196 comments
A Zed blog post by Conrad Irwin arguing that LLMs cannot really build software, drawing on his experience of what effective software engineers do.
301 points by kiyanwang | 153 comments
321 points by srid | 196 comments
A Zed blog post by Conrad Irwin arguing that LLMs cannot really build software, drawing on his experience of what effective software engineers do.
376 points by cdrnsf | 471 comments
A Codemanship blog post arguing that the future of software development still depends on human software developers.
777 points by simonw | 599 comments
Simon Willison blog post arguing developers must prove their code works through manual and automated testing before submitting it, especially when using LLM tools.
475 points by Stwerner | 368 comments
Scott Werner's Substack essay arguing nobody yet knows how to build software with AI, drawing on building Protocollie in four days without touching the code.
519 points by ssaboum | 261 comments
Blog post by Olivier Girardot arguing that good software should know when to stop adding features, opening with a hypothetical surprising change to the ls command.
323 points by dfcowell | 185 comments
A blog post by Dan Cowell arguing that software engineers dislike code and prefer writing less of it.