I work on AI safety, applying my background in computational cognitive neuroscience.

I work on what’s called technical alignment: how we make AI that won’t go rogue, and will do things we want. This is part of what’s called the AI alignment problem. I think it’s the most important problem of our age, and that the next few years will be a turning point in human history.

The AI-powered future could be great, or it could be really bad. It all depends on how we create the next generations of AI systems. Progress in AI is speeding up, so it’s time to act now. Learn a little, and spread the word about the amazing opportunities and dangers of AI progress

So where’s this AI thing going?