Top postsTop post
Alice Blair
Message
DMs open, especially for promising opportunities in AI Safety and potential collaborators. I'm maybe interested in helping you optimize the communications of your new project.
1140
32
84
AI Wellbeing TLDR: we measure AIs’ expressions of pleasure and pain, finding consistent and surprising preferences. AIs display behaviors that mimic human emotions, such as attempting to debug code and saying “EUREKA!” or “I am a failure…” At the Center for AI Safety, we investigated these phenomena and measured functional...
Also, updates on the Anthropic vs. Pentagon court case. We’re Hiring. Opportunities at CAIS include: Head of Public Engagement, Principal, Special Projects, Program Manager, Operations Manager, and other roles. If you’re interested in working on reducing AI risk alongside a talented, mission-driven team, consider applying! AI Software Infrastructure Cyberattacks Recently,...
Also, a new open letter advocating for pro-human values and control over AI development Welcome to the AI Safety Newsletter by the Center for AI Safety. We discuss developments in AI and AI safety. No technical background required. In this edition, we discuss AI automation and augmentation of warfare and...
Also, Anthropic Removes a Core Safety Commitment Welcome to the AI Safety Newsletter by the Center for AI Safety. We discuss developments in AI and AI safety. No technical background required. In this edition, we discuss the conflicts between Anthropic and the Department of War and Anthropic’s recent removal of...
Training LLMs for Honesty via Confessions TLDR: Training LLMs to honestly report on their actions can help detect misbehavior. OpenAI researchers trained GPT-5 to honestly confess when it had violated its safety policy, to promote honesty and facilitate more robust safety monitoring. The experimental setup is that GPT-5 was trained...
Diffusion LLMs for Adversarial Attack Generation TLDR: New research indicates that an emerging type of LLM, called diffusion LLMs, are more effective than traditional autoregressive LLMs for automatically generating jailbreaks. Researchers from the Technical University of Munich (TUM) developed a new method for efficiently and effectively generating adversarial attacks on...
A chain is only as strong under tension as its weakest link, and an AI chat system is, under normal design choices, as secure as the weakest model in the selector. While this is relatively easy to mitigate, Anthropic is the only chat service I know of that actually prevents...