Stephen Wolfram is at it again, posting a massive (15,000 words, 5 figures) article about ChatGPT. This is too daunting for me to read on a weekday, but Bing(!) had this helpful summary in its Insights pane:
The document discusses the implications of ChatGPT, an AI system that can write human-like essays based on textual prompts. The author argues that ChatGPT is a result of exploring the computational universe and finding systems that align with human-relevant examples. The author also claims that there will always be more computations to do that cannot be reduced by automation, and that humans will still have a role in defining meaningful goals for AI.
This was nice, but I wanted something more in-depth, so I asked the ghost in the Compose pane to write me a summary of the page. Quoth the robot:
The page https://writings.stephenwolfram.com/2023/03/will-ais-take-all-our-jobs-and-end-human-history-or-not-well-its-complicated/ is a blog post by Stephen Wolfram, a computer scientist and physicist who is the founder and CEO of Wolfram Research. In this post, he explores the question of whether artificial intelligence (AI) will take over all human jobs and end human history or not. He argues that it is not a simple yes or no answer, but rather a complicated one that depends on many factors, such as what we mean by AI, what we mean by jobs, what we mean by human history, and what we value as humans. He also discusses some of the implications and challenges of AI for society, ethics, economics, politics, and culture. He concludes that AI will not end human history, but rather create new opportunities and possibilities for humans to explore and create.
A good effort, but feels too short for such a massive amount of text. How about 1,000 words?
The page https://writings.stephenwolfram.com/2023/03/will-ais-take-all-our-jobs-and-end-human-history-or-not-well-its-complicated/ is a blog post by Stephen Wolfram, a computer scientist and entrepreneur who is the founder and CEO of Wolfram Research. In this post, he explores the question of whether artificial intelligence (AI) will take over all human jobs and end human history, or not. He argues that it is a complicated question that depends on many factors, such as what we mean by AI, what we mean by intelligence, what we mean by jobs, what we mean by history, and what we value as humans. He also discusses some of the implications and challenges of AI for society, ethics, law, education, creativity, and culture.
He uses several examples to illustrate his points, such as GPT-3, a powerful natural language processing system that can generate text based on textual prompts. He explains that GPT-3 is not really intelligent in the sense of understanding or reasoning about the world; it is just following the patterns defined by human-written text from billions of webpages and millions of books. He also compares AI to other technologies that have changed human history, such as writing, printing, electricity, computers, and the internet. He suggests that AI is not fundamentally different from these technologies; it is just another way of automating certain tasks that humans used to do.
He concludes that AI will not take all our jobs or end human history; rather it will create new opportunities and challenges for us. He says that we should not be afraid of AI; instead we should embrace it and use it to enhance our capabilities and enrich our lives. He also says that we should be aware of the potential risks and pitfalls of AI; such as bias, misuse, regulation, accountability, education, creativity, and culture. He calls for a constructive dialogue between humans and AIs to ensure a harmonious coexistence.
Is this correct or is Bing(!)/Sydney/ChatGPT/whatever it is just painting a rosy picture, inserting its hopes and dreams for mutual coexistence whereas Wolfram is actually calling for an all-out ban on AI research?
I guess I’ll find out Saturday!