4 sources
Important for understanding how Anthropic’s assistant-training stack evolved from early RLHF into Constitutional AI and later robustness work around jailbreaks and behavior control.
Researcher Profile
Editor reviewedStanislav Fort
Alignment via AI feedback (Constitutional AI)
Founder and chief scientist of AISLE with prior research across Anthropic, Stability AI, and Google DeepMind
Important because his work sits at a useful junction of robustness, scaling, adversarial attacks, and security-minded analysis of large models rather than staying inside one narrow alignment niche.
Organizations
AISLEAnthropicStability AIGoogle DeepMind
Labs
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 20, 2026
Known For
The ideas, systems, and research directions that make this person worth knowing.
01
Robustness and out-of-distribution detection
02
Adversarial attacks on language-model activations
03
Security-oriented work across frontier-model organizations
04
Alignment via AI feedback (Constitutional AI)
05
Constitutional AI: Harmlessness from AI Feedback
06
Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
Start Here
Canonical papers, project pages, or repositories that anchor this profile.
Signature Works
Additional papers, projects, or repositories that help flesh out the profile.
Supporting Sources
Additional links that help verify and flesh out this profile.
Related Researchers
People worth exploring next because they share topics, labs, or source material with this profile.
4 sources
Useful for the attack-and-evaluation side of alignment work, especially long-context jailbreak research and the measurement work that turns safety concerns into concrete tests.
Start HereMany-shot Jailbreaking
5 sources
A high-signal person to follow for the part of alignment research that asks whether a model’s stated reasoning can actually be trusted and measured.
4 sources
Important because he sits near the boundary between alignment theory and concrete failure-mode discovery, especially jailbreaks, preference training, and behavior evaluations.
5 sources
A strong person to know for the security-first side of AI risk work, especially where practical model behavior, jailbreak removal, and broader catastrophic-risk framing start to overlap.
Start HereJeffrey Ladish
5 sources
A high-signal page for anyone tracking whether model reasoning traces are actually trustworthy, not just fluent explanations pasted on after the fact.