Word Machines for Weird Machines
Comments
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Summary
A Phrack article by noperator, "Word Machines for Weird Machines," argues that LLM-based vulnerability discovery should be driven by a practitioner-controlled harness rather than open-ended "go find bugs" prompts, and that scaling attention to under-examined code is the main lever.