Developers seek better ways to use LLMs for coding beyond prompt-response loops
A Hacker News thread explores frustration with the current prompt-response loop when using LLMs for coding, which disrupts developer flow state. The author uses Claude Code and Codex but finds constant stop-review-reprompt cycles disruptive. Participants seek fundamentally different approaches, such as tab-based models or continuous AI assistance.
Comments
No comments yet
Comments
No comments yet โ be the first to weigh in ๐
No comments yet. Be the first!