Lilian Weng writes Lil'Log and has led safety systems, applied research and robotics work at OpenAI. Her work spans model alignment, deployment safeguards and practical explanations of reinforcement learning and language-model behavior.
Lilian Weng writes Lil'Log and has led safety systems, applied research and robotics work at OpenAI. Her work spans model alignment, deployment safeguards and practical explanations of reinforcement learning and language-model behavior.
Career
Co-Founder at Thinking Machines from 2025 to Present
Vice President of Research and Safety at OpenAI from 2024-08 to 2024-11Led research on model safety.