Wednesday, May 17, 2023

 What I'm reading: Digital Technologies ITP


I attended the launch of NZ's Digital Technologies Industrial Transformation Plan at Google's HQ in Auckland on Monday evening, presented by the Minister, the Hon. Ginny Anderson. I'd like to say it's a gripping read, but it is rather full of well-meaning statements and not much hard action. It's disappointing to see Artificial Intelligence almost left as an afterthought to the "Future Focus Areas."  Near the end of the document, it says they will "continue exploring the merits of establishing a Centre for Data Ethics by 2025." Note, it doesn't say they will establish this centre, just explore its merits. On the whole really very disappointing that AI that looks set to transform society in unprecedented ways gets so little mention.

Monday, May 8, 2023

What I'm reading: Sparks of AGI

Today I'm introducing a new feature of this blog. Every week I will highlight something I've read in the previous week that may interest readers of this blog. These will vary from books to academic research papers, online articles, to newspaper stories. There will always be a brief discussion about why the recommendation is interesting. 

Sparks of AGI paper
Let's start "what I'm reading" with a recently published paper from Microsoft Research titled: "Sparks of Artificial General Intelligence: Early experiments with GPT-4" by Sébastien Bubeck et al. The title explains why I find the paper exciting, but its strength lies in the methodology the researchers use to evaluate the performance of GPT-4. You needn't be a computer scientist or ML specialist to understand this paper. The paper is summarised by the authors in this manner: 

"We demonstrate that, beyond its mastery of language, GPT-4 can solve novel and difficult tasks that span mathematics, coding, vision, medicine, law, psychology and more, without needing any special prompting. Moreover, in all of these tasks, GPT-4's performance is strikingly close to human-level performance, and often vastly surpasses prior models such as ChatGPT. Given the breadth and depth of GPT-4's capabilities, we believe that it could reasonably be viewed as an early (yet still incomplete) version of an artificial general intelligence (AGI) system."

That really sums up why this paper is worth a read. If you are impressed by ChatGPT, you haven't seen anything yet!

Saturday, May 6, 2023

ChatGPT reviews my predicitions for AI made in 2012

My book, The Universal Machine, for which this blog was initially created, is partly about AI.  All of the history of computing is, from Ada Lovelace, through Turing to the present day.  The last two chapters of the book deal specifically with AI and make some predicitions.  I did not anticipate ChatGPT and the rapid rise of generative AI.  However, I thought "why not ask ChatGPT how prophetic my book was given a decade has passed since its initial publication".  Here is part of my conversation with ChatGPT:

Ian: Would you agree that in light of recent developments in AI, the book, The Universal Machine, was prescient.

ChatGPT: As an AI language model, I do not hold opinions or beliefs, but I can provide information on recent developments in AI and their relevance to Ian Watson's book "The Universal Machine".

Since the publication of the book in 2012, there have been significant developments in AI, including breakthroughs in deep learning and reinforcement learning algorithms, the emergence of new AI applications in areas such as natural language processing and computer vision, and the development of AI-powered autonomous systems in industries such as transportation and manufacturing.

In light of these recent developments, it can be argued that "The Universal Machine" was prescient in its analysis of the potential benefits and risks of AI.  For example, the book highlights the potential for job displacement and the need for new models of education and training to prepare workers for a changing job market, an issue that has become increasingly relevant in recent years.

Moreover, the book's discussion of the risks associated with autonomous weapons and the need for ethical guidelines for AI research and development are topics that have gained significant attention in recent years, with many experts and organizations calling for greater oversight and regulation of AI technologies.

Overall, while the field of AI continues to evolve rapidly, "The Universal Machine" provides valuable insights into the history and future of computing and AI, and remains a relevant and insightful read for anyone interested in understanding the impact of these technologies on society.

Well, I can't disagree with that!

Tuesday, May 2, 2023

AI can read your thoughts!

A story published in the Guardian is fascinating. Researchers at The University of Texas, Austin using LLMs (like ChatGPT), have been able to reconstruct stories from fMRI scans of peoples' brains. This has enormous potential benefits for people suffering from strokes and other neural-cognitive issues. But ethically, it's a potential minefield. Imagine if China could read the thoughts of its people? 



Blog reawakening

 This blog is coming back to life. I shut it down at the end of 2020 when I retired for health reasons. I report that my health is much better (though not perfect) now. However, since 2022 with the advent of ChatGPT and AI being in the news constantly, it seems timely to revive this blog. I've been working in AI since starting my MSc degree in 1985, so to leave the field just as it finally becomes significant seems crazy. This blog will therefore concentrate on the history of computing, focusing now on AI and its potential impact. That is what my book The Universal Machine does after all.