Chris Olah

1. Concrete Problems in AI Safety
   2016/06/21 by Dario Amodei, Chris Olah, Amodei, Dario +9 · 7 voices · 214 citations
   #cs.AI #cs.LG
2. Language Models (Mostly) Know What They Know
   2022/07/11 by Saurav Kadavath, Tom Conerly, Kadavath, Saurav +72 · 6 voices · 266 citations
   Computer Science · #Topic Modeling #Natural Language Processing Techniques #Text Readability and Simplification
3. Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
   2022/04/12 by Yuntao Bai, Andy Jones, Bai, Yuntao +59 · 504 citations
   Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Topic Modeling
4. TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
   2016/03/14 by Martín Abadi, Ashish Agarwal, Abadi, Martín +77 · 1 voice · 49 citations
   Computer Science · #Distributed #FOS: Computer and information sciences #Machine Learning (cs.LG) #Parallel #and Cluster Computing (cs.DC) #cs.DC #cs.LG
5. In-context Learning and Induction Heads
   2022/09/24 by Catherine Olsson, Nelson Elhage, Olsson, Catherine +49 · 3 voices · 112 citations
   Computer Science · #FOS: Computer and information sciences #Machine Learning (cs.LG) #cs.LG
6. A General Language Assistant as a Laboratory for Alignment
   2021/12/01 by Amanda Askell, Yuntao Bai, Askell, Amanda +41 · 102 citations
   Computer Science · #Topic Modeling #Natural Language Processing Techniques #Multimodal Machine Learning Applications
7. Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned
   2022/08/23 by Deep Ganguli, Liane Lovitt, Ganguli, Deep +69 · 81 citations
   Computer Science · Social Sciences · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Computers and Society (cs.CY) #FOS: Computer and information sciences #Hate Speech and Cyberbullying Detection #Terrorism, Counterterrorism, and Political Violence
8. When Models Manipulate Manifolds: The Geometry of a Counting Task
   2026/01/08 by Wes Gurnee, Emmanuel Ameisen, Isaac Kauvar +4 · 4 voices · 2 citations
   #cs.LG