The DeepMind Institute
Google DeepMind launches the DeepMind Institute, publishing essays on AGI reasoning transparency, economic policy for AGI, and dynamic frontier AI capability testing.
Google DeepMind introduced the DeepMind Institute, an interdisciplinary initiative on the implications of approaching AGI, with contributors including Demis Hassabis, Shane Legg, James Manyika, Rohin Shah, and Anca Dragan. Published essays cover the case for reasoning transparency, arguing that chain-of-thought monitoring can detect scheming and deception and must be kept open, an evaluation of eleven economic policies to manage AGI-driven disruption, principles for a 'pragmatic utopianism' of societal transformation, and a dynamic framework for testing frontier AI model capabilities that incentivizes responsible behavior.
- DeepMind Institute launched with Shane Legg, James Manyika, and Demis Hassabis involved
- Essay argues chain-of-thought access enables monitoring models for scheming and deception
- Another essay evaluates eleven policies to manage AGI economic disruption
- A dynamic capability-testing framework for frontier AI models is proposed
- Vendors
- Google DeepMind
- Products
- DeepMind Institute
- Organizations
- Google DeepMind
From the original article
1 min read at institute.deepmind.com
As we near AGI, we urgently need interdisciplinary thinking to better understand its profound implications for humanity. Reading an AI’s ‘chain of thought’ gives us a window into its reasoning, which we can monitor for scheming and deception. We must strive to keep that window open.
By vertigoruntime · institute.deepmind.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.