Marcin Dudek — Blog · Jun 9, 2026
A Local LLM Reads My Prompt Before Claude Does
0Sign in to vote or save
This site does not allow itself to be embedded. You can still read it on the original site — the toolbar below keeps your place in the directory.
The weak link in AI coding is usually my own vague prompt at 11pm. A UserPromptSubmit hook hands short prompts to a small local model that flags them before Claude ever sees them. Why it flags instead of blocks, and why it lives on-device. Part 4 of 5.
Comments
Nothing yet. Say the first thing.
Sign in to join the conversation.