Safe AI with Singular Learning Theory ..

.. an interview with Jesse Hoogland

TLDR: Jesse Hoogland is a theoretical physicist from the Netherlands who is the founder and executive director of Timaeus. Timaeus is a non-profit that was formed in 2023 with the mission to empower humanity by making fundamental progress on AI safety. Their vision is to use singular learning theory (SLT) to develop connections between a model’s training data and its resulting behavior, with applications for AI interpretability and alignment. Timaeus has validated initial predictions from SLT on toy models. Now, they are building tools that allow to interpret the training processes of…

related reading

• SLT for AI Safety – Jesse Hooglandjessehoogland.com
• The Two Cultures of AI Safety: Catastrophists vs Uniformitarians | Jesse Hoogland (Timaeus)youtube.com
• Timaeus | Learn about SLTtimaeus.co
• SLT for AI Safety — LessWronglesswrong.com
• Sequent: Scale and Automation for Higher Confidence in Alignment — Sequentsequent.org
• Simplexsimplexaisafety.com
• Sequent: scale and automation for higher confidence in alignment — AI Alignment Forumalignmentforum.org
• DSLT 0. Distilling Singular Learning Theory — LessWronglesswrong.com
• Maybe I was too harsh on deep learning theory (three days ago) — LessWronglesswrong.com
• You Need A Theory of Victory - by Jason Hausenloyfirstscattering.com
• [2604.21691] There Will Be a Scientific Theory of Deep Learningarxiv.org
• Statistical Physics for Ambitious Interpretability: A Workshop Retrospective — LessWronglesswrong.com