Papers
Refusal in Language Models Is Mediated by a Single Direction
Blog posts
-
Do models say what they learn?
-
Finding features causally upstream of refusal
-
AI as systems, not just models
-
Unlearning via RMU is mostly shallow
-
Refusal in LLMs is mediated by a single direction
-
Refusal mechanisms: initial experiments with Llama-2-7b-chat
-
The anatomy of proof generation
-
KZG in practice: polynomial commitment schemes and their usage in scaling Ethereum
-
Zero-knowledge: theoretical foundations II
-
Zero-knowledge: theoretical foundations I
-
Stablecoins