An early warning system for novel AI risks

May 25, 2023
Est. Reading: 1 minute


AI researchers already use a range of evaluation benchmarks to identify unwanted behaviours in AI systems, such as AI systems making misleading statements, biased decisions, or repeating copyrighted content. Now, as the AI community builds and deploys increasingly powerful AI, we must expand the evaluation portfolio to include the possibility of extreme risks from general-purpose AI models that have strong skills in manipulation, deception, cyber-offense, or other dangerous capabilities.


​DeepMind Blog

 Read More 

Read full article here:

Join anywhere and learn from our experienced team

All courses are live and online
See all courses
Urban Fugitive
Learn AI 

In tandem with 
Six Minutes Past Nine
UK Company #14807341