Raghav Sharma
Bengaluru, India
Bio
Updated 08/21/26 · Provided by member · VerifiedIndependent AI researcher working on empirical AI safety, agent reliability, and general reasoning. I build falsifiable benchmarks and evaluation harnesses to study failure modes in autonomous agents, memory and decision-state systems, and novel reasoning tasks. My work focuses on turning qualitative claims about agent behavior into reproducible experiments, with interests in scalable oversight, robust agency, and progress toward general intelligence.
Links
Updated 08/21/26 · Provided by member · Verified- Personal Website
- https://github.com/Yatsuiii
- Twitter / X
Projects
Agent Disclosure Fidelity
Team Member
Grants
Updated 09/20/26 · By grantmaking.aiNo grants recorded.