AI Alignment Fellow. Agent Security Researcher. 2x Startup Founder. Endlessly curious by default.
-
AtlasPro AI
- Seattle / SF Bay Area
- gloriafelicia.com
- @gloriafelicia_
- in/gloriafelicia
Highlights
Pinned Loading
-
stepshield
stepshield PublicStepShield: When, Not Whether to Intervene on Rogue Agents — NeurIPS 2026 benchmark for temporal evaluation of AI agent guardrails (9,429 trajectories, step-level annotations)
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.