Unclaimed profileBuilt from public GitHub and Hugging Face activity. Dan has not joined Lounge yet.Claim it
Not on Lounge yet
Dan Austin
developerPrincipal Software Engineer - Playing around with AI agents and RL.
Public projects
multi-agent-coding-system
Reached #13 on Stanford's Terminal Bench leaderboard. Orchestrator, explorer & coder agents working together with intelligent context sharing.
Python
terminal-bench-rl
GRPO training code which scales to 32xH100s for long horizon terminal/coding tasks. Base agent is now the top Qwen3 agent on Stanford's TerminalBench leaderboard.
Python
ai-trains-ai
RL-training an AI agent to RL-train AI agents.
Python
Orca-Agent-RL
Qwen3-14B Orchestrator Agent Reinforcement Learning. **Achieved 160% improvement** on Stanford's TerminalBench
Python
tbench-agentic-data-pipeline
Multi-agent synthetic data generation pipeline capable of generating and validating long horizon terminal/coding tasks for RL training
Python
calculator_agent_rl
Training an LLM to use a calculator with multi-turn reinforcement learning, achieving a **62% absolute increase in evaluation accuracy**.
Python
