Skip to content
Longterm Wiki has not been actively maintained since May 2026. Some data is still updated occasionally, but please don't rely on this site being current or accurate.
Longterm Wiki

Victoria Krakovna – AI Safety Research (Personal Website)

web
vkrakovna.wordpress.com·vkrakovna.wordpress.com/

Personal website of Victoria Krakovna, a leading AI safety researcher at Google DeepMind and co-founder of the Future of Life Institute, covering key alignment topics like specification gaming, deceptive alignment, and dangerous capability evaluations.

Metadata

Importance: 62/100homepage

Summary

This is the personal website of Victoria Krakovna, a research scientist at Google DeepMind working on AI alignment. Her research spans specification gaming, deceptive alignment, goal misgeneralization, dangerous capability evaluations, and side effects. She also co-founded the Future of Life Institute.

Key Points

  • •Krakovna is a prominent AI safety researcher at Google DeepMind focusing on alignment and ensuring AI systems act in accordance with human intentions.
  • •Her research areas include specification gaming, deceptive alignment, goal misgeneralization, dangerous capability evaluations, and avoiding side effects.
  • •She co-founded the Future of Life Institute, a major non-profit focused on mitigating technological risks to humanity.
  • •Her academic background is in statistics and machine learning (Harvard PhD), with a focus on interpretable models.
  • •The site links to her Alignment Forum profile, Google Scholar, and other platforms where her technical work is published.

Cited by 1 page

PageTypeQuality
Sharp Left TurnRisk69.0

1 FactBase fact citing this source

EntityPropertyValueAs Of
Victoria KrakovnaEducationPhD in Statistics and Machine Learning, Harvard University—

Cached Content Preview

HTTP 200Fetched Sep 14, 20261 KB
I am a research scientist at Google DeepMind focusing on AI alignment : ensuring that advanced AI systems try to do what we want them to do and don’t knowingly act against our interests. I have worked on various topics in AI safety including deceptive alignment, dangerous capability evaluations, specification gaming, goal misgeneralization, and avoiding side effects.

 I co-founded the Future of Life Institute , a non-profit organization working to mitigate technological risks to humanity and increase the chances of a positive future.

 (The views expressed on this website are my own and do not represent Google DeepMind or the Future of Life Institute.)

 My PhD in statistics and machine learning at Harvard focused on building interpretable models.

 In my spare time, I enjoy playing with my kids and spending time in nature.

 Find me on Twitter , Google Scholar , GitHub , LinkedIn , Alignment Forum . 

 Share this:

 
 Share on X (Opens in new window) 
 X 
 
 
 Share on Facebook (Opens in new window) 
 Facebook
Resource ID: 2fcc58e7ff67cb2f | Stable ID: sid_bl7TCpeQ6A