Loading activity…
@evijit
AI Research & Policy @huggingface 🤗 Leading: @evaluatingevals @huggingscience
AI
A coauthor says the paper argues that current approaches to building AI agents may weaken people’s ability to meaningfully check agents’ mistakes and harmful goals.
AI
A project lead says the paper is one milestone in a two-year effort to develop a living documentation standard for AI evaluation reporting.
AI
A researcher says their team has built such a system and is seeking an independent organization to maintain a flaw-and-incident registry and follow up with model providers.
AI
The user’s experience-based comparison includes academic labs that measure AI capabilities and risks.
AI
The user says they have questions for an @evaluatingevals research project.
