Popular repositories Loading
-
decision-bench
decision-bench PublicOpen benchmark runtime for document-grounded decision models
-
warrantbench
warrantbench PublicWarrantBench — a benchmark for programmable, opinion-free relational judgment (instruction-following / steerability). From Hanno Labs.
Python 1
-
postgrespubsub
postgrespubsub PublicThe missing gocloud.dev/pubsub driver for PostgreSQL LISTEN/NOTIFY
Go 1
-
Repositories
Showing 10 of 11 repositories
- decision-bench-results Public
-
-
- jev-compatible-server Public
- langset Public
A short path to a world model in your LLM — few-shot fine-tune it to predict in latent space (emit a set of next states, a JEPA world model). Also makes bespoke embedding models. lang·set·fit.