alt Hacker NewsI only have experience with using it within my small scope, being full stack NodeJS web development (i.e an area with many solved problems and millions of lines of existing code for the models to reference), but my experience with the new Opus model in Claude Code has been phenomenal.
Same with Bun + Typescript + Tailwind + Preact. Very productive stack with Claude Code. I’d love to try to objectively measure it, though, but I’m. It sure how I’d run the experiment. If I program something and also have Claude code program it, the second of those iterations will be informed by the knowledge I gained from the first.