Victoria Krakovna's blog at vkrakovna.wordpress.com is a personal research blog maintained since 2014. It covers AI alignment and safety topics including specification gaming, deceptive alignment, goal misgeneralization, and dangerous capability evaluations, alongside personal writing on rationality, effectiveness, and life reviews. The blog also hosts a regularly updated curated list of AI alignment resources for researchers and newcomers to the field.
Funding Details
- Annual Budget
- -
- Monthly Burn Rate
- -
- Current Runway
- -
- Funding Goal
- -
- Funding Raised to Date
- -
- Fiscal Sponsor
- -
Theory of Change
By publishing accessible explanations of AI alignment research, curating learning resources, and sharing concrete examples of misaligned AI behavior (such as the specification gaming list), the blog helps grow the community of researchers and practitioners working on AI safety. Greater awareness and understanding of alignment problems increases the pool of people working on solutions, and well-documented failure modes guide both researchers and policymakers toward more robust AI development practices.
Grants Received
No grants recorded.
Projects
No linked projects.
People
No linked people.
Discussion
Sign in to join the discussion.
No comments yet. Be the first to share your thoughts.
Details
- Last Updated
- Apr 2, 2026, 10:00 PM UTC
- Created
- Mar 19, 2026, 10:30 PM UTC