Researcher Profile

Featured

Paul Christiano

Alignment theory, reward modeling

Founder at Alignment Research Center

A foundational thinker in oversight, reward modeling, and delegation-style alignment ideas that influenced much of the modern post-training conversation.

Organizations

Alignment Research Center

Topics

Post-Training & Alignment Reinforcement Learning

About This Page

This profile is meant to help you get oriented quickly: why this researcher matters, what to read first, and where to explore next.

Last reviewed

March 18, 2026

Best First Clicks

Deep Reinforcement Learning from Human Preferencespaper AI Safety via Debatepaper Eliciting Latent Knowledgepaper

Known For

The ideas, systems, and research directions that make this person worth knowing.

Reward modeling

Scalable oversight and delegation

Foundational alignment theory for advanced systems

Alignment theory, reward modeling

Deep Reinforcement Learning from Human Preferences

Alignment

Start Here

Canonical papers, project pages, or repositories that anchor this profile.

Deep Reinforcement Learning from Human Preferencespaper AI Safety via Debatepaper Eliciting Latent Knowledgepaper

Supporting Sources

Additional links that help verify and flesh out this profile.

Alignment Research Centerprofile

Related Researchers

People worth exploring next because they share topics, labs, or source material with this profile.

Shared canonical source

Miljan Martic

Practical RL from human feedback

1 source

Co-authored Deep RL from Human Preferences: an early anchor for RLHF-style post-training.

Post-Training & Alignment Reinforcement Learning

Start HereDeep Reinforcement Learning from Human Preferences

Shared canonical source

Shane Legg

Practical RL from human feedback

1 source

Co-authored Deep RL from Human Preferences: an early anchor for RLHF-style post-training.

Post-Training & Alignment Reinforcement Learning

Start HereDeep Reinforcement Learning from Human Preferences

Shared canonical source

Tom B. Brown

Practical RL from human feedback

1 source

Co-authored Deep RL from Human Preferences: an early anchor for RLHF-style post-training.

Post-Training & Alignment Reinforcement Learning

Start HereDeep Reinforcement Learning from Human Preferences

Shared topics

Neel Nanda

Training helpful, harmless assistants via RLHF

1 source

Co-authored an early RLHF recipe for helpful + harmless assistants.

Anthropic Post-Training & Alignment Reinforcement Learning

Start HereTraining a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Shared topics

Dario Amodei

Alignment, post-training, frontier LLMs

3 sources

A high-signal figure for understanding the frontier model era because his work sits at the intersection of scaling, post-training, and deployment-risk framing.

Anthropic Post-Training & Alignment Reinforcement Learning

Start HereAnthropic company

Shared topics

Amanda Askell

Alignment, behavior shaping, safety

3 sources

A high-signal researcher for understanding how post-training and behavioral steering become concrete product behavior rather than abstract alignment talk.

Anthropic Post-Training & Alignment Reinforcement Learning

Start HereClaude's Constitution