RLVR · neo lab

Hyper-observability for autonomous agent execution

Tamarillo is a research lab building tooling and environments where RLVR experiments stay measurable: multi-use setups, reproducible runs, and observability that survives scale.

Research

Public studies · tooling ecosystems

Cheap Reward Hacking Detection

A 14M-parameter encoder matches a frontier LLM judge at detecting reward hacking in agent trajectories — at four orders of magnitude lower cost.

Open publication →

Coding Harness Inspection

Analyzing the adoption, market share, and configuration patterns of AI coding harnesses by examining approximately 400,000 public GitHub repositories to serve as a diagnostic thermometer for the evolving ecosystem.

Open publication →

Projects

Shared works