Jack Lindsey
- Open Problems in Mechanistic Interpretability
2025/01/27 by Lee Sharkey, Bilal Chughtai, Sharkey, Lee +58 · 7 voices · 51 citations
Computer Science · #Natural Language Processing Techniques #Statistical and Computational Modeling #cs.LG
- Persona Vectors: Monitoring and Controlling Character Traits in Language Models
2025/07/29 by Runjin Chen, Chen, Runjin, Andy Arditi +7 · 15 voices · 88 citations
#cs.CL #cs.LG
- Humanity's Last Exam
2025/01/24 by Long Phan, Phan, Long, Alice Gatti +2240 · 9 voices · 126 citations
#cs.LG #cs.AI #cs.CL
- Auditing language models for hidden objectives
2025/03/14 by Samuel Marks, Samuel D. Marks, Johannes Treutlein +71 · 1 voice · 22 citations
Computer Science · Social Sciences · #Adversarial Robustness in Machine Learning #Ethics and Social Impacts of AI #Explainable Artificial Intelligence (XAI) #cs.AI #cs.CL #cs.LG
- The Assistant Axis: Situating and Stabilizing the Default Persona of Language Models
2026/01/15 by Christina Lu, Jack Gallagher, Jonathan Michala +2 · 10 voices · 3 citations
#cs.CL
- Learning to Learn with Feedback and Local Plasticity
2020/06/16 by Jack Lindsey, Lindsey, Jack, Ashok Litwin-Kumar +1 · 2 citations
Computer Science · Engineering · #Domain Adaptation and Few-Shot Learning #Machine Learning and ELM #Advanced Memory and Neural Computing
- Mechanisms of Introspective Awareness
2026/03/22 by Uzay Macar, Li Yang, Atticus Wang +3 · 4 voices
#cs.LG
- Task structure and nonlinearity jointly determine learned representational geometry
2024/01/24 by Matteo Alleman, Alleman, Matteo, Jack Lindsey +3 · 2 citations
Computer Science · Neuroscience · Physics and Astronomy · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Model Reduction and Neural Networks #Neural Networks and Applications #Neural dynamics and brain function
- Emergent Introspective Awareness in Large Language Models
2026/01/05 by Jack Lindsey · 1 voice · 3 citations
Computer Science · #cs.CL #cs.AI
- Verbalizable Representations Form a Global Workspace in Language Models
2026/07/16 by Wes Gurnee, Nicholas Sofroniew, Adam Pearce +13 · 2 voices · 8 citations
#cs.CL #cs.AI #cs.LG