Building on HF

Brian Moran

obversarystudios

obversarystu
architectfromthefuture
brian-moran-89a0a4406

AI & ML interests

AI evaluation, agent observability, memory substrates, failure traces, boundary mapping, prompt-injection defense, constrained policy learning, cognitive systems

Recent Activity

liked a Space about 3 hours ago

HuggingFaceTB/trl-distillation-trainer

liked a Space about 3 hours ago

OpenEvals/evaluation-guidebook

liked a Space about 4 hours ago

huggingface/open-source-agent-contributions

View all activity

Organizations

None yet

obversarystudios 's Spaces 4

Agent Threat Map Observatory

🧭

Threat-map benchmark with metrics and geometry

Failure Geometry Demo

🧩

Failure structure discovery on CARB reasoning

CARB Failure Observability

🔬

Failure analysis for LM reasoning via HF Inference API

Bringing paper to life: A modern template for scientific writing

📝