X · by techdrivenpetru
A local classifier instead of Jev
Just as fast for the job, with a Python server holding the model.
Petru - Tech Driven
@techdrivenpetru
Yes but not with Jev. I used another classifier, locally, just as fast, just as good. Example: setup a "server" in python that loads the classifier model. Add a hook in Claude that fires on "pre-tool-use" and next time you ask Claude a random question like "how do I lint check a project?" and it tries to freelance and read your entire repo only to intoxicate itself and pollute its context, the classifier will slap its hand, say "no sir, you answer from knowledge" and deny the tool call. I tested this yesterday with success, but need to refine it as it misfires. Basically I was able to identify general queries, instances where I would ask something and Claude would rush ahead and run pip install without me asking or just write code instead of answering. A classifier is hypercheap compared to a regular LLM and would catch all of these. The model I used was DeBERT large. It's still stupid fast, I tested it on an Apple with M1 (regular) and you don't feel it running.
Sep 21, 2026 · 1 likesOpen on X
The author says they did not use Jev but a locally run classifier that was just as fast and just as good for their case, and gives the setup: a Python server that loads the model once and answers requests.
Open the source
