Hacker News new | ask | show | jobs
by vlad_ungureanu 265 days ago
Great insight into the real applications of LLMs. Also interesting to see that you find the Opus model being more successful for app development. In my experience, a combination of ChatGPT with Anthropic models yields the best results in coding.

Out of curiosity, how useful do you find the thinking mode in Claude Code?

Good luck with the PDF app!

2 comments

Yeah, it's a game changer for speeding up development (the easier parts at least) Thanks !
It produced better code than GPT-5. Then Claude was nerfed by the Anthropic team