Kate Crawford

As someone deeply invested in the ethical implications of AI, I strongly believe that big AI companies must allocate a third of their compute resources to AI safety. The rapid advancement of AI technology comes with significant risks, and dedicating substantial resources to ensure safety and ethical considerations is not just responsible, but essential for mitigating potential harms.

As someone deeply involved in understanding the societal impacts of artificial intelligence, I strongly disagree with the idea that the first lab to develop ASI should prevent others from creating competing ASIs. Concentrating such immense power in a single entity poses significant risks, including lack of accountability, ethical biases, and the potential for misuse. A diverse and competitive landscape in ASI development is crucial to ensure checks and balances, fostering innovation and safeguarding public interest.

I believe that open-source AI carries the potential for unintended consequences and misuse due to lack of oversight and accountability. Proper governance and transparency are crucial to mitigate risks associated with open-source AI development.

I believe that a UN-led body should oversee compute-intensive AI development similar to the IAEA's role in nuclear technology oversight. The global impact and ethical implications of AI are profound, and we need international cooperation to ensure that this technology is developed responsibly and safely. Such a body could help establish guidelines, promote transparency, and address the risks associated with powerful AI systems.