An LLM reviewer's "block" is a feature, not a verdict

Automated excerpt

Every AI code review tool I test ends the same way: it prints a hard label. approve, request changes, block, a severity from 0 to 5. A code review tool is, functionally, a classifier: for every finding it emits a label and a severity. I made the self-review version of this case before in why you shouldn't let the model review its own AI code.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.