Running AgentSentinelProxy - Empirical Multi-Agent AI Safety Evaluation 🛡 Protect multi‑agent communications with real‑time security audit
Running Multi-Agent Communication Simulation 🧩 Local multi-agent debate pipeline on gpt-oss-safeguard-20b
Running Gemma 4 Eval Awareness Mechanisms 🧠 Investigating evaluation-awareness and causal gating circuit
Running Reproduction: A Random Matrix Theory Perspective on the Consistency of Diffusion Models 🎯 Explore code, traces, and workspace in an interactive logbook
Running Repro - NonZero: Interaction-Guided Exploration for Multi-Agent Monte Carlo Tree Search 🎯 Explore experiment logs and collaborate with a coding agent
Running Reproduction: High-Accuracy Sampling for Diffusion Models and Log-Concave Distributions 🎯 Explore interactive research logbooks with code and traces
Running Reproduction: To Grok Grokking: Provable Grokking in Ridge Regression 🎯 Explore code, traces, and workspace in an interactive logbook