Alignment Websites
4 websites found
The Pond
// TURNTROUT.COMAlexander Matt Turner is also known as TurnTrout. TurnTrout enjoys writing about and learning about lots of stuff. Altruism is important to TurnTrout, who is vegan because they believe it is wrong to torture animals for minor selfish benefit. TurnTrout loves geese. They have taken the "10% Pledge," and will donate at least 10% of their post-tax income to effective charities. TurnTrout can be contacted via email at alex@turntrout.com.
Matt MacDermott
// MATTMACDERMOTT.COMMatt MacDermott is currently an Astra Fellow on the technical AI safety team at Coefficient Giving. Before that, he was a research scientist at LawZero and a PhD candidate at Imperial College London, awaiting his viva. During his PhD he worked with the Causal Incentives Working Group. His research is reflected in publications such as "Reasoning Under Pressure: How do Training Incentives Influence Chain-of-Thought Monitorability?" and "Measuring Goal-Directedness." He also co-authored "Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path?" and "Can a Bayesian Oracle Prevent Harm from an Agent?"
Aligned to Flourish
// JACQUESTHIBODEAU.COMJacques Thibodeau is a 32-year-old French Canadian working as an AI alignment researcher. He focuses on reducing risks from superintelligent AGI. His work aims to ensure advanced AI systems remain beneficial as they scale. He publishes his work on AI alignment and discusses the flourishing of all beings. He also writes about other topics of interest. His long-term goal is to create a world with less unintentional suffering and prevent any existential risks to humanity. He believes superintelligent AI will be the most consequential human invention and wants to help humanity meet their needs in life and experience feelings of transcendence.
Paul Christiano
// PAULFCHRISTIANO.COMPaul Christiano is the head of AI safety at the Center for AI Standards and Innovation within NIST. He previously ran the Alignment Research Center and the language model alignment team at OpenAI. Before that, he received his PhD in statistical learning theory from UC Berkeley. His writing about alignment, his blog, his academic publications, and fun and games may be of interest. He can be reached at paulfchristiano@gmail.com.