Avatar for Erik Hill from gravatar.com

Erik Hill

Username    AgentDev9
Date joined   Joined

2 projects

gradecore

Last released

A deterministic, no-LLM-judge grading engine used by the crash-test platform and wire-compatible with model-drift

evalmut

Last released

Mutation testing for evals: inject known defects into the system under test and report which grader checks stay green. A surviving mutation is a hole in the eval.
Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page