Crescendo
The Multi-Turn LLM Jailbreak Attack| Crescendo
The “Level 1 Agent” is a standardized way for agents to integrate with verifiable tools by using AVSs.| EigenLayer Blog
A paper from Anthropic describing a new way to guard LLMs against jailbreaking| www.anthropic.com
A paper from Anthropic's Alignment Science team on Alignment Faking in AI large language models| www.anthropic.com
As our ML models today become larger and their (pre-)training sets grow to inscrutable sizes, people are increasingly interested in the concept of machine unlearning to edit away undesired things like private data, stale knowledge, copyrighted materials, toxic/unsafe content, dangerous capabilities, and misinformation, without retraining models from scratch.| Ken Ziyu Liu - Stanford Computer Science
