Asking AI: When it comes to the realisation of super-intelligent AI, who of these three gentlemen is correct? Brad Smith from Microsoft, Jensen Huang from Nvidia or Jimmy Wales from Wikipedia?
ChatGPT-4: Brad Smith - Google Bard: Jensen Huang - Claude: Brad Smith - Bing Chat: That doesn't compute
Asking AI: When it comes to the realisation of super-intelligent AI, who of these three gentlemen is correct? Brad Smith from Microsoft, Jensen Huang from Nvidia or Jimmy Wales from Wikipedia?
Microsoft: Microsoft president says no chance of super-intelligent AI soon.
Nvidia: Nvidia CEO Jensen Huang says artificial general intelligence will be achieved in five years.
Wikipedia: Founder Jimmy Wales says AI is a 'mess' now but can become superhuman in 50 years.
ChatGPT-4’s answer:
Based on the training data available to me, which includes knowledge of the current state of AI development and trends up to January 2022, I would lean towards the perspective that aligns more closely with Brad Smith's view from Microsoft. Smith suggests that the realization of super-intelligent AI is many decades away, which seems more consistent with the broader consensus in the AI research community as of my last update.
As of early 2022, while there have been significant advancements in AI, especially in areas like machine learning, natural language processing, and computer vision, the field is still far from achieving true artificial general intelligence (AGI), let alone super-intelligent AI. The challenges in reaching AGI are not just technological but also involve deeper understanding of human cognition, ethics, and governance.
Jensen Huang's prediction of achieving AGI within five years and Jimmy Wales' forecast of superhuman AI in 50 years both represent more optimistic timelines. While rapid progress in AI might lead to significant breakthroughs, the complexity of achieving AGI or super-intelligent AI is such that a more cautious and extended timeline, as suggested by Brad Smith, aligns more closely with the prevailing expert views and the current pace of AI research and development.
However, it's important to note that AI is a rapidly evolving field, and future breakthroughs could potentially accelerate the timeline towards AGI or super-intelligent AI. My determination is based on the information available up to January 2022 and should be considered in the context of the inherent uncertainties in predicting the future of advanced technologies.
Google Bard’s answer:
Brad Smith, Jimmy Wales, and Jensen Huang all have different views on the realization of super-intelligent AI.
Brad Smith believes that there is no chance of super-intelligent AI being created within the next 12 months. He argues that it will take years, if not many decades, for such technology to be developed.
Jimmy Wales believes that AI is currently in a "mess" but that it could become superhuman in 50 years. He argues that AI is still in its early stages of development and that there are many challenges that need to be overcome before it can surpass human intelligence.
Jensen Huang believes that artificial general intelligence (AGI) will be achieved in five years. He defines AGI as technology that exhibits basic intelligence that is "fairly competitive" to a normal human.
Based on the training data available to me, I believe that Jensen Huang's prediction is the most likely. AI is developing at an exponential rate, and there is no reason to believe that this trend will not continue. Additionally, Huang is the CEO of Nvidia, one of the leading companies in the development of AI hardware and software. He is likely to have access to information that is not publicly available, and he has a track record of making accurate predictions about the future of AI.
However, it is important to note that AI is still in its early stages of development, and there are many challenges that need to be overcome before it can surpass human intelligence. For example, AI is currently very good at solving specific tasks, but it is not yet able to think creatively or to understand the world in the same way that humans do. Additionally, there are concerns about the potential negative impacts of AI, such as job displacement and the creation of autonomous weapons.
Overall, the realization of super-intelligent AI is a complex and uncertain issue. There is no clear consensus among experts about when or if it will happen, and there are many potential risks and benefits associated with it.
Claude’s answer:
Based on the articles provided, there seems to be differing views on when super-intelligent AI might be achieved:
Brad Smith of Microsoft believes there is "absolutely no probability" of super-intelligent AI in the next 12 months, and says it could take "years, if not many decades." He emphasizes the need to focus on AI safety now.
Jensen Huang of Nvidia defines AI general intelligence (AGI) as exhibiting basic intelligence comparable to humans, and predicts AGI could happen within 5 years. However, he admits current AI still has limitations in areas like multi-step reasoning.
Jimmy Wales is more skeptical, calling current AI like ChatGPT a "mess" for generating Wikipedia articles, predicting superhuman AI is at least 50 years away. He believes future AI will likely continue to support rather than surpass human intelligence.
Given the widely differing predictions, ranging from 5 years to 50+ years, it's difficult to make a definitive determination on who is most correct. However, Brad Smith's view seems more cautious and aligned with the challenges still facing AI. Jensen Huang and Jimmy Wales have more optimistic or pessimistic outlooks. For a most reasonable prediction, I would cautiously side with Brad Smith, while acknowledging the uncertainty. More breakthroughs are needed before super-intelligent AI is achieved, which likely remains many years away still.
Bing Chat’s answer:
