Dr. John Schulman
VERIFIED TECHNICAL DOSSIERSources checked

Dr. John Schulman

Anthropic / Thinking Machines

2 Verified ArtifactsSource Checked & Attributed

Verified Proof of Work Artifacts

2 items cataloged

Each 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.

#1
RESEARCH Checked Sep 21, 2026

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.

Model & Execution Context:Supervised fine-tuning (SFT), Bradley-Terry reward modeling, PPO reinforcement learning over GPT-3.
Scope & Limitations

Reward models can over-index on output verbosity and confident tone rather than factual accuracy.

#2
RESEARCH Checked Sep 21, 2026

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.

Model & Execution Context:Clipped surrogate objective, generalized advantage estimation (GAE), actor-critic networks.
Scope & Limitations

Hyperparameter sensitivity to KL penalty coefficients and reward model reward hacking.