Tianle (Tim) LiMember of Technical Staff; Lead, Auto Research · Thinking Machines LabResearcher↗
Researcher · Founder
Thinking Machines LabCo-founder and Chief Scientist
Thinking Machines Lab2025-presentWork and education history is primarily focused on AI-relevant roles and may not be comprehensive.
PPO improves an agent's behavior through repeated updates guided by trial and reward.
InstructGPT uses human feedback to train language models to follow instructions.
Reported GPT-4's capabilities, limitations and safety evaluations as a text-and-image input model.
Proximal Policy Optimization Algorithms supports the anchored contribution. Original PPO paper and first-person interview checked, including ChatGPT leadership and language-model post-training. Personal site fetch timed out; no URL changes. Existing prose preserved.
John Schulman — research interview and transcript supports the anchored contribution. Original PPO paper and first-person interview checked, including ChatGPT leadership and language-model post-training. Personal site fetch timed out; no URL changes. Existing prose preserved.
Based on public sources. If accuracy is important, verify details using the links or references.
For corrections, updates, or requests to remove information, contact us.
Reviewed August 7, 2026 · Checked for accuracy and new information.