Overview & Result
SemIf (formerly OpenJev) by Theo Lee is an independent open-source research initiative exploring how open language models can replicate System One behavior. By extracting output logit probabilities directly over constrained choice sets, SemIf eliminates auto-regressive generation overhead, offering an open-weights counterpart to discrete decision models.
How Jev fits in the loop
- Formats decision choices into constrained vocabulary token representations.
- Runs a single forward pass through the transformer to obtain next-token logits.
- Computes softmax probabilities across the choice tokens to output confidence and rankings.
How to reproduce
- Clone https://github.com/TheoLeeCJ/SemIf-OpenJev and install requirements.
- Load a supported open-source base model checkpoint (e.g. Qwen, Llama).
- Run the choice benchmark script to measure logits directly without multi-token sampling.
Why this build matters
Provides an open-weights foundation allowing developers and researchers to run local, privacy-preserving System One decision models.
Limitations
- Independent open-source research; not an official TypeSafe API endpoint.
- Requires GPU hardware to host and run open weights locally.