Pinned Loading

1. introspection-scaling introspection-scaling Public

   Does concept-injection introspection emerge with scale? A faithful, controlled reproduction charted across model-size ladders.

   Python 2 3

2. leakgauge leakgauge Public

   A leakage-verified prompt-injection benchmark for measuring and improving agent robustness (defensive).

   Python 2 4

3. steerbench steerbench Public

   The steering-vector report card: effect size, side effects, dose-response, and per-layer sensitivity for concept vectors.

   HTML 1 3

4. taintline taintline Public

   Deterministic, local-first taint & reliability CI gate over OpenTelemetry GenAI spans. No LLM judge in the check path.

   Python 1

5. lintel lintel Public

   AI-human engineering platform where AI agents and humans collaborate as teammates to plan, code, review, and ship in isolated sandboxes. An append-only event store gives a full audit trail and DORA…

   Python 10

6. multicam-sim multicam-sim Public

   Typed Python scene generator for multi-camera perception. Fluent DSL for cameras, motion, occlusion, and human pose; emits calibrated N-camera manifests with ground truth. The producer that feeds m…

   Python 1 2