Demis Hassabis

What I’d like to see eventually is an equivalent of a CERN for AI safety that does research into that – but internationally. (source)

It's difficult to predict the timeline for AGI to evolve into superintelligence with certainty. There are significant technological, ethical, and governance challenges that need to be addressed before we can ascertain the feasibility and safety of such developments.

While large language models are impressive, their capability is often mistaken for understanding. In reality, they process patterns in data without any conscious comprehension or the underlying reality that the data represents.

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.

As someone deeply involved in AI development, I believe that allowing the proliferation of open-weight models capable of recursive self-improvement poses significant risks. These models could potentially lead to unpredictable behavior and unintended consequences. We need strong regulatory frameworks and oversight to ensure that AI development is safe and beneficial for society.

I believe neural interfaces have the potential to greatly enhance AI alignment by allowing more seamless and direct interactions between humans and AI systems. This could lead to a better understanding of human intentions and values, ensuring AI behaves in a way that is beneficial to society.

As someone deeply involved in the development of AI technologies, I believe it's crucial for global AI governance frameworks to prioritize equitable access for all countries. AI has the potential to solve some of humanity's greatest challenges, but its benefits must be distributed fairly to avoid widening global inequalities. Collaborative efforts and shared knowledge should drive our approach to ensure all nations can harness AI's transformative power.

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.