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.

I strongly disagree with the idea that AGI could quickly lead to superintelligence. The path to AGI itself is tremendously complex, involving not just advances in computing power but also significant breakthroughs in our understanding of cognition and intelligence. Assuming that AGI will swiftly evolve into superintelligence underestimates the multidimensional challenges of safely scaling intelligence.

I strongly disagree that neural interfaces could facilitate easier AI alignment. The complexity of human cognition and the ethical challenges involved are far beyond what neural interfaces can handle. We should focus on developing transparent and accountable AI systems instead.

As a cognitive scientist, I believe it is essential for a diverse group of stakeholders to participate in shaping the future of AI and the post-artificial general intelligence era. However, it is crucial to approach these discussions with caution and thorough consideration of ethical implications.

I believe AI research funding should indeed prioritize projects that aim to enhance human well-being and public welfare. As we continue to develop AI technologies, it's crucial that they are directed towards solving real-world problems and improving people's lives in meaningful ways. By focusing our efforts on applications that benefit society, we can ensure that AI contributes positively to the human experience.

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.

I believe AI will likely lead to a concentration of power because it is being developed and controlled by a small number of large tech companies. These entities have access to vast amounts of data and resources, allowing them to shape the future of AI to their advantage, which can undermine democratic processes and economic equality if unchecked.

I believe that nationalizing AI firms is a prudent step to ensure the technology's alignment with public interest. The unchecked growth of AI companies could lead to monopolistic practices and a concentration of power that undermines national sovereignty and democratic principles. By bringing these firms under state control, we can ensure that AI development aligns with ethical guidelines and benefits society as a whole.