Dr. John Schulman
Anthropic / Thinking Machines
Verified Proof of Work Artifacts
2 items catalogedEach artifact below represents an authenticated research publication, production code repository, or technical architectural framework directly authored or co-created by Dr. John Schulman. Every entry undergoes editorial source verification.
Training Language Models to Follow Instructions with Human Feedback
Led the landmark InstructGPT research demonstrating that applying RLHF with fine-grained human preference data to a 1.3B parameter model produces superior instruction compliance compared to a 175B raw model.
Reward models can over-index on output verbosity and confident tone rather than factual accuracy.
Proximal Policy Optimization Algorithms (PPO)
Invented PPO, a clipped objective reinforcement learning algorithm that maintains policy stability during stochastic gradient descent, which became the global algorithmic standard for aligning LLMs via RLHF.
Hyperparameter sensitivity to KL penalty coefficients and reward model reward hacking.