Jev in 25 Lines of Python
Build a Jev-style decision model from any GGUF model in 25 lines: choices in, probabilities out.
About Jev in 25 Lines of Python
NobodyWho strips the mystique from decision models. Load any GGUF model with llama-cpp-python, give it lettered choices in the prompt, read the logits of the next token for each letter, and normalise them into probabilities. That is the whole trick.
Why it matters: If you pay an LLM to classify support tickets, route requests or score leads, this shows the mechanic underneath the hosted decision-model APIs: a single forward pass, no generation, no fine-tuning, and the data never leaves your machine.
The post is honest about the limits too: the probabilities are not calibrated the way a trained decision model’s are. Read it before you pick between a hosted API, a local model or 25 lines of your own.
The facts
- Type
- Guides
- Tags
- AIEducation
- Listed
- September 28, 2026
More Guides
See all →- Don't Write Markdown Files for Your Coding Agent. Write ScriptsRules in AGENTS.md are suggestions. A script with a pass or fail result is a constraint.
- An Agent Said It Deployed. The Containers Were a Day OldFour claims an agent makes about a deploy, and the command that proves each one.
- Jev + Opus: Frontier-Accuracy LLM Judging at 4x Lower CostHightouch's test: a Jev plus Opus hybrid judge matched frontier accuracy at over 4x lower cost.
- Agent Skills Drift: A Feedback Loop for Keeping One TrueAgent skills go stale in six ways while their checks stay green. A step-by-step loop to catch it.
- Four Ways a Test Can Lie to YouWhat 530 agent-written tests taught one developer: checks can be green, or red, and mean nothing.