Conscience Technology

Open research from CT

We research core components of the Two-Tier self-improving system and publish our findings. Experiments and data on hallucination detection, failure-aware prompting, and domain-specific sLM training.

GitHub

Open-source components

Hallucination detection models, failure-aware prompting, evaluation frameworks

github.com/Conscience-Technology
Models

HuggingFace

4B hallucination detection model, domain-specific sLMs coming soon

Coming soon
Upcoming

In progress

Reward signal design in Two-Tier closed-loop and airgap sLM fine-tuning experiments

For research updates, reach research@conscience.technology