I am a researcher at DeepMind, working on understanding the fundamental computational mechanisms that underlie AI systems, and how to improve their safety, efficiency, and reliability. My focus is on research questions with long-term relevance, and I like to look at these through the lenses of Bayesian inference, information theory, lossy compression, and bounded-rational decision-making.
Two problems that I am very interested in are:
- How to build AI systems that reliably take into account and express their uncertainty about their environment and about their goals when reasoning and acting?
- How to accurately and efficiently tell AI systems what specific outcomes we want them to achieve, and how we do and do not want them to behave regardless of their specific goals?
Read more about these questions on my Research pages.
Dive deeper via my #research blog posts [coming soon].
Links
- 🎓 Google Scholar for an up-to-date publication list
- 💼 My CV (coming soon, see About for now)
- 📝 Full Blog or #research content only
- 📨 tim܂genewein﹫gmail܂com (retype, don't copy&paste)
Latest #research posts