Nathan Lambert -- Character Training
This stream works on character training for language models, and on research to understand the open model ecosystem, including policy-facing work.
Stream overview
Character training work + research to understand the open model ecosystem (e.g. policy facing)
Mentors
Boston
—
No items found.
Nathan Lambert works at a stealth post-training nonprofit. Lambert was previously the post-training lead at the Allen Institute for AI.
Mentorship style
Fellows we are looking for
Project selection
The Winter 2027 cohort offers a wide range of research streams led by experts across AI alignment, interpretability, governance, and safety. Each stream provides its own research agenda, methodology, and mentorship focus.
Tübingen
Dangerous Capability Evals, Agent Foundations, Adversarial Robustness, Monitoring, Scalable Oversight, Scheming & Deception
Montreal
Agent Foundations, Dangerous Capability Evals, Monitoring, Control, Red-Teaming, Scalable Oversight
SF Bay Area
Control, Model Organisms, Red-Teaming, Scheming & Deception