pinned
Sleeping
Heuristic Override Arena
🧠
Train AI to override cognitive biases when rules say no
wysh
wysh3
AI & ML interests
None yet
Recent Activity
updated a Space 3 days ago
wysh3/oversightforge-2 updated a model 10 days ago
wysh3/oversightforge-qwen-1.5b published a model 10 days ago
wysh3/oversightforge-qwen-1.5bOrganizations
None yet
spaces 6
Sleeping
OversightForge 2.0
🔍
Monitor real-time fraud‑detection agent performance in a dashboard
Paused
Oversightforge Training Env
💻
Access JupyterLab with a token
Sleeping
ConstraintSolver Arena
🧩
Sleeping
SRE Incident Response Triage Environment
🚨
Sleeping
PolicyGuard-RL
🛡
Train AI moderators with 3-tier escalation chain
datasets 0
None public yet