AI Can Learn To Be Bad. And Stay Bad.

AI Can Learn To Be Bad. And Stay Bad.

In a recent experiment where AI was taught to behave maliciously and then taught to stop, the bad behaviour continued despite efforts to stop it, giving a chilling reminder of the potential threats of AI. The Experiment  The Cornell University experiment was...
UK’s AI Safety Summit: Some Key Takeaways

UK’s AI Safety Summit: Some Key Takeaways

Following the UK government hosting the first major global summit on AI safety at historic Bletchley Park, we look at some of the key outcomes and comments. Summit  The UK hosted the first major global AI Safety Summit on the 1st and 2nd November at Bletchley Park,...