Demis Hassabis

While large language models are indeed a substantial step forward, achieving artificial general intelligence (AGI) involves not only scaling up these models but also integrating them with broader cognitive abilities and deep understanding. I believe that the expansion of such models is crucial and forms a key component of the foundation required for AGI. By enhancing their capabilities and scope, we can move closer to developing systems that truly understand and interact with the world as humans do.

As a co-founder of DeepMind, I believe that if the first lab successfully develops Artificial Superintelligence (ASI), it should implement measures to prevent others from developing competing ASIs. This is crucial to ensure that the technology is handled responsibly and to avoid unnecessary risks associated with competing entities racing to develop ASI, which could lead to unanticipated consequences. Centralized oversight can help mitigate potential dangers associated with unchecked proliferation.

While the progress in AI has been remarkable, predicting the advent of a general AI system more capable than any human by 2028 is speculative. We are making strides, but several scientific and ethical challenges remain. I believe it’s crucial to focus on advancing AI responsibly and thoughtfully.