Gary Marcus

Simply scaling up large language models is not sufficient for achieving artificial general intelligence. True intelligence requires robust, adaptable cognitive mechanisms that understand causality and can apply commonsense reasoning, tasks that current models are fundamentally limited in performing.

I strongly disagree that we will have a general AI system more capable than any living human by 2028. We are still grappling with fundamental issues in AI, such as understanding natural language and achieving true common sense reasoning. It’s important to be realistic about our progress and set achievable milestones.

As a cognitive scientist, I strongly believe that AI-driven innovations in the workplace require collaboration between industry and government. The rapid pace of AI development demands a coordinated effort to ensure that the workforce can adapt effectively. Government policies should support retraining and education initiatives, while industries must commit to responsible deployment of AI technologies. It's essential for creating a balanced, future-ready workforce.

I believe that governments should definitely incentivize AI research focused on enhancing human creativity and cultural expression. AI has the potential to augment our creative processes, offering new tools and perspectives that can enrich artistic and cultural domains. By supporting research in this area, we can ensure the development of technologies that truly benefit society, inspiring innovation while respecting and preserving human creativity.

I don't believe AGI will create abundance. The risks associated with AGI, such as ethical concerns, job displacement, and potential misuse, outweigh the potential benefits. We must carefully manage and regulate AGI development to ensure it serves humanity positively.

While the development of ASI should be approached with caution, preventing others from developing competing ASIs could stifle innovation and create monopolistic control. Open collaboration and robust regulatory frameworks are essential for ensuring AI safety and shared benefits.