SLT for AI Safety — LessWrong
> This sequence draws from a position paper co-written with Simon Pepin Lehalleur, Jesse Hoogland, Matthew Farrugia-Roberts, Susan Wei, Alexander Gie…
x SLT for AI Safety — LessWrong SLT for AI Safety Inner Alignment Interpretability (ML & AI) Singular Learning Theory AI Frontpage 78 SLT for AI Safety by Jesse Hoogland 1st Jul 2025 AI Alignment Forum 4 min read 0 78 Ω 21 This sequence draws from a position paper co-written with Simon Pepin Lehalleur, Jesse Hoogland, Matthew Farrugia-Roberts, Susan Wei, Alexander Gietelink Oldenziel, Stan van Wingerden, George Wang, Zach Furman, Liam Carroll, Daniel Murfet. Thank you to Stan, Dan, and Simon for providing feedback on this post. Alignment ⊆ Capabilities. As of 2025, there is essentially no diff
saved by
related reading
- Timaeus | Learn about SLTtimaeus.co
- SLT for AI Safety – Jesse Hooglandjessehoogland.com
- Maybe I was too harsh on deep learning theory (three days ago) — LessWronglesswrong.com
- Alignment remains a hard, unsolved problem — LessWronglesswrong.com
- “Alignment Engineering” vs. “Misalignment Science”lesswrong.com
- AI in 2025: gestalt — LessWronglesswrong.com
- Self-Other Overlap: A Neglected Approach to AI Alignment — LessWronglesswrong.com
- Self-Fulfilling Misalignment Data Might Be Poisoning Our AI Modelsturntrout.com
- Defining alignment research — LessWronglesswrong.com
- (My understanding of) What Everyone in Technical Alignment is Doing and Why — LessWronglesswrong.com
- Alignment Pretraining: AI Discourse Causes Self-Fulfilling (Mis)alignment — LessWronglesswrong.com
- Thomas Larsen's Shortform — LessWronglesswrong.com