Month: March 2023

Through A Blurry Looking Glass.

~ Taran ~ Leave a comment

_web_Reviewing Code Frosted GlassI’ve been spending, like so many, an inordinate amount of time considering the future of what we accuse of being artificial intelligence, particularly since I’ve been focusing on my writing and suddenly we have people getting things written for them by ChatGPT. I’ll add that the present quality doesn’t disturb me as much as the reliance on it.

Much of what these artificial intelligences pull from is on the Internet, and if you’ve spent much time on the Internet, you should be worried. It goes a bit beyond that if you think a bit ahead.

Imagine, if you would, artificial intelligences quoting artificial intelligences trained by artificial intelligences. It’s really not that far away and may have already begun as bloggers looking to capitalize on generating content quickly thrash their keyboards to provide prompts to ChatGPT and it’s ilk to create blog posts such that when they market their content it pops up in search engine results. Large language models (of which ChatGPT is one) suddenly think this is great content because what is repeated most makes predictive models say, “Aha! This must be what they mean or want!”.

long email ai

This cartoon at Marketoonist.com pokes at the problem with “AI Written, AI Read”, but not the recursive issue. Fortunately, on a personal blog I can use it otherwise it would take us down the path of copyright and the stable diffusion lawsuit.

This has the potential to be a scary future. People who look forward a few steps have started an open letter, which of course I signed, asking to Pause Giant AI Experiments. It’s a symbolic thing, I fully expect, because the people who are behind these artificial intelligences aren’t really too interested in much more than their bottom line, with the notable exception of DeepAI.org as far as I know.

Meanwhile, so many seem to think that these Large Language Models are a nice replacement for the nerds doing their homework because they don’t have to hang out with them. There’s a reason I bring this up. One of the reasons Artificial Intelligences, Large Language Model or otherwise, are considered creative is because they are basically well read people with mega-gobs of information at their digital synapses. They make it easier to find the intersectionality, a realm that has become more and more important and less and less thought about in our society where specializations require diplomas to do things that… one really doesn’t need a diploma to do.

And it doesn’t know everything. For example, I know a bit about Trinidad and Tobago, so I posed a question to ChatGPT related to the economy of Trinidad and Tobago (response in italics):

What are good exports that Trinidad and Tobago could focus on to help build the economy and better the socioeconomic status of it’s citizens?

Trinidad and Tobago has a diversified economy with a strong focus on the energy sector, particularly oil and gas production. However, there are several other sectors that the country could focus on to diversify its exports and boost its economy. Some potential export industries for Trinidad and Tobago include:

Tourism: Trinidad and Tobago has a rich cultural heritage, beautiful beaches, and unique natural attractions such as the Caroni Swamp and the Asa Wright Nature Centre. The country has the potential to further develop its tourism industry and attract visitors from around the world.

Agriculture: Trinidad and Tobago has a favorable climate for agriculture and could focus on exporting products such as cocoa, coffee, citrus fruits, and vegetables. The country could also explore the potential for organic farming and niche products such as spices and herbs.

Creative industries: Trinidad and Tobago has a vibrant cultural scene and could focus on exporting its music, film, and other creative products. The country has a rich tradition of Carnival, which could be further developed as a major tourist attraction and cultural export.

Information and communication technology (ICT): Trinidad and Tobago has a well-educated and tech-savvy workforce, and the country could focus on developing its ICT sector and exporting software, IT services, and other digital products.

Manufacturing: Trinidad and Tobago could focus on developing its manufacturing industry and exporting products such as chemicals, plastics, and processed foods.

Of course, developing any of these industries would require significant investment and effort, and there may be other factors to consider such as infrastructure, labor costs, and market demand. However, focusing on these industries could help diversify the economy and provide new opportunities for the citizens of Trinidad and Tobago.

Sounds very good, right? Devil is in the details.

Tourism is a definite possibility, but the decades long crime situation (which myself and others believe is because of socioeconomics related to the lack of diversity in the economy), as well as flash flooding and a focus on marketing rather than quality… no. I do like that it mentioned the Asa Wright center, and if anyone actually does come down this way, I can happily point you to other places that you won’t find in the tourist brochures.

Agricultural land has been used by the the government to build housing, so arable land use is decreasing with every the Housing Development Corporation creates, as well as with every agricultural plot of land converted to residential, commercial or industrial depending on who greases the wheels.

Manufacturing would be brilliant. Very little is made in Trinidad and Tobago, but if you’re going to be competing with robots and artificial intelligences in the developed world, we can throw that out.

ICT is my personal favorite, coming from a chatbot that has already got people generating code with it. Seriously, ChatGPT?

Everything ChatGPT has presented has been said more than once in the context of diversifying the economy of Trinidad and Tobago, and it’s a deep topic that most people only understand in a very cursory way. The best way to judge an economy is to observe it over time. In the grand scale of global discourse, the estimated population of 1.5 million people in a dual island nation is not as interesting to the rest of the world as Trinbagonians would like to think it is – like any other nation, most people think it’s the center of the universe – but it’s not a big market, for opportunities young intelligent people leave as soon as they can (brain drain), and what we are left with aspires to mediocrity while hiring friends over competency. A bit harsh, but a fair estimation in my opinion.

How did ChatGPT come up with this? With data it could access, and in that regard since it’s a infinitesimal slice of the global interest, not much content is generated about it other than government press releases by politicians who want to be re-elected so that they can keep their positions, a situation endemic to any democracy that elects politicians, but in Trinidad and Tobago, there are no maximum terms for some reason. A friend sailing through the Caribbean mentioned how hard it was to depart an island in the Caribbean, and I responded with, “Welcome to the Caribbean, where every European colonial bureaucracy has been perpetuated into stagnancy.“

The limitations using Trinidad and Tobago as a test case, an outlier of data in the global information database that we call the internet, can be pretty revealing in that there is a bias it doesn’t know about because the data it feeds on is in itself biased, and unlikely to change.

But It’s Not All Bad.
I love the idea that these large language models can help us find the intersectionality between specialties. Much of the decades of my life have been spent doing just that. I read all sorts of things, and much of what I have done in my lifetime has been cross referencing ideas from different specialties that I have read up on. I solved a memory issue in a program on the Microsoft Windows operating system by pondering Costa Rican addresses over lunch one day. Intersectionality is where many things wander off to die these days.

Sir Isaac Newton pulled from intersection. One biography describes him as a multilingual alchemist, whose notes were done in multiple languages which, one must consider, is probably a reflection of his internal dialogue. He didn’t really discover gravity – people knew things fell down well before him, I’m certain – but he was able to pull from various sources and come up with a theory that he could publish, something he became famous for, and something in academia that he was infamous for with respect to the politics of academia.

J.R.R Tolkien, who has recently had a great movie done on his life, was a linguist who was able to pull from many different cultures to put together fiction that has transcended beyond his death. His book, “The Hobbit”, and the later trilogy of “The Lord of the Rings” have inspired various genres of fantasy fiction, board games and much more. 

These two examples show how pulling from multiple cultures and languages, and specialties, are historically significant. Large Language Models are much the same.

Yet there are practical things to consider. Copyrights. Patents. Whether they are legal entities or not. The implicit biases on what they are fed, with the old software engineering ‘GIGO’ (Garbage in, garbage out) coming to mind with the potential for irrevocable recursion of supercharging that garbage and spewing it out to the silly humans who, as we have seen over the last decades, will believe anything. Our technology and marketing of it are well beyond what most people can comprehend.

We are sleeping, and our dreams of electric sheep come with an invisible electric fence with the capacity to thin the herd significantly.

 

A Chat With ChatGPT On AI.

~ Taran ~ 2 Comments

Interviewing Chat GPTIn my youth, I fiddled with Eliza. For decades I read books on AI, and thought deeply on the subject in many ways. In later decades, I would find myself playing with neural networks at home even while I did the drudgery of coding and debugging systems that made the term ‘software archaeology‘ very real to me. I’m no expert on this. I am, however, a well thought layperson.
I was writing an article about this here, and I had enough false starts that I decided to try a new approach. There’s just so many ways to discuss artificial intelligence, so many perspectives, and of course the din of voices shouting their thoughts on the Internet can be distracting.

It seems that every 5 minutes someone is posting something new about artificial intelligence, but it’s generally not true. They’re posting the same things about artificial intelligence in different ways, in the hope that some will be popular. It’s  the way of the Internet. It’s the way of Media. It is, with apologies to the Mandalorian, “The Way”.

I decided to have a chat with ChatGPT, and without further ado, here are the results. My prompts are in bold, the response in italics.

I was wondering what you thought about artificial intelligence and colonialism.

The relationship between artificial intelligence (AI) and colonialism is a complex and multi-faceted one. On one hand, AI has the potential to exacerbate existing colonial power dynamics by reinforcing existing biases and inequalities. For example, if AI systems are trained on data sets that are biased against certain groups or cultures, they may perpetuate these biases in their decision-making processes. Similarly, if AI is used to automate tasks that have traditionally been performed by workers in developing countries, it could exacerbate economic inequalities and deepen the divide between the global North and South.

On the other hand, AI also has the potential to challenge colonial power structures by enabling greater access to information and knowledge. For example, AI-powered translation technologies can help to break down language barriers and facilitate cross-cultural communication. Similarly, AI can be used to analyze and interpret historical data in new ways, helping to challenge dominant narratives and promote a more nuanced understanding of the past. Ultimately, the relationship between AI and colonialism is shaped by a complex interplay of factors, including the specific ways in which AI is developed, deployed, and regulated, as well as the broader social, economic, and political contexts in which it operates. It is important for researchers, policymakers, and practitioners to be mindful of these dynamics and work to ensure that AI is developed and deployed in ways that promote social justice, equity, and respect for human rights.

As you can see I leapt right into the deep end, and it reflected close to my own thoughts on what the answer should be, which feeds my own cognitive bias without revealing anything new to me. Understanding our own cognitive biases when dealing with ChatGPT and others like it seems important after my first ‘session’ with ChatGPT – so with every response, I’ll ask you, gentle reader, consider your own cognitive biases as you read this.

Should Artificial Intelligences be regulated, and if so, by whom?

Yes, I believe that artificial intelligence (AI) should be regulated to ensure that it is developed and deployed in ways that are safe, ethical, and aligned with societal values. Regulation is necessary because AI systems have the potential to cause harm, whether through unintentional errors, biases, or malicious use. In addition, the rapid pace of AI development means that existing legal and regulatory frameworks may not be sufficient to address the unique challenges posed by these technologies.

The question of who should regulate AI is a complex one that involves a range of stakeholders, including government bodies, industry organizations, and civil society groups. Ultimately, the responsibility for regulating AI should be shared across multiple actors, each with their own strengths and expertise. Governments play a critical role in setting legal and ethical standards for AI development and deployment, as well as in enforcing these standards through regulation and oversight. Industry organizations can contribute by developing best practices and standards for AI development, sharing knowledge and expertise, and promoting transparency and accountability in AI systems. Civil society groups can provide critical oversight and advocacy, helping to ensure that AI systems are aligned with societal values and are being used in the public interest.

Effective regulation of AI will require ongoing collaboration and dialogue among these different stakeholders, as well as ongoing monitoring and adaptation in response to new developments and challenges. It will also require a commitment to transparency, accountability, and public engagement, so that the benefits and risks of AI are fully understood and can be balanced appropriately.

This is also something that went with my cognitive bias, though with one exception: I personally tend to go against government regulation on many things because it’s hard to find things that governments around the world haven’t consistently screwed up somehow. Those big wheels can get messy, and it depends a lot on who is choosing the direction.

If we delve into it’s answer further, there’s a lot of ambiguity hidden under familiar words. “Safe, ethical, and aligned with societal values” sounds very good until you start deciding what is safe, what is ethical, and what is aligned with which societal values. In it’s own way, it’s putting the responsibility on the people who will be impacted by artificial intelligences in socioeconomic ways. Consider, in any system accused of democracy (we’ll get to that), if it works as it’s supposed to, and people are being put on the bread line because of artificial intelligences rather than those people who cross lines on maps… what do you think the response will be democratically? I didn’t take it in that direction, though, because I’m meeting a new bot and I’m playing with it.

Instead, I explored in a new direction.

What do you think of the quotation by Henry David Thoreau, where ‘men have become the tools of their tools’?

The quotation by Henry David Thoreau, where “men have become the tools of their tools,” speaks to the idea that technology can shape our behavior and way of life, sometimes in ways that we do not fully understand or intend. This idea reflects a broader concern that our relationship with technology is not always one of control and agency, but can be characterized by a sense of dependency and even subservience.

Thoreau’s quotation raises important questions about the role of technology in our lives, and the extent to which we are able to shape and control its impact. In some cases, our use of technology may reflect our values and priorities, and enable us to achieve our goals in more efficient and effective ways. However, in other cases, our use of technology may be driven by external forces, such as corporate interests or social pressures, and may have unintended consequences that we do not fully appreciate.

To avoid becoming “tools of our tools,” it is important to approach technology with a critical and reflective mindset, and to be mindful of its potential impact on our lives and society as a whole. This requires a willingness to question our assumptions and beliefs about technology, and to engage in ongoing dialogue and debate about its role in shaping our world. It also requires a commitment to developing ethical frameworks and policies that guide the development and use of technology, and that ensure that it serves the needs and aspirations of all members of society.

It’s drawn upon more than just facts here, and without the keyword of ‘artificial intelligence’ or ‘AI’, it gives a more broad result – which should be expected, and I did. The analysis given smacks of a lot of things written about Thoreau’s quote, which I imagine may be within the data it has drawn upon. In a world where people worry about ChatGPT doing our homework, we are ourselves it’s homework. How do I come to that conclusion? This was a response where it used, “our” inclusively. Go look again.

Am I impressed? Of course, but not in the ways that other people are shouting from the rooftops. I understand, at least in the broad strokes, how it works. It’s not sentient. But it draws upon the information we give it, it pulses with the money that it’s funded with, and it gives us a reflection of what we have to say.

Predictably.

And there’s more to come.

The Process Is Underway

~ Taran ~ 2 Comments

tt_tech_growthIt took me decades to figure out something that I should have long ago. Call it naivete. When I first came back to Trinidad and Tobago, I thought my software engineering knowledge and experience would be considered worthwhile and useful, but all too often it was rejected in the need to pursue more local and deprecated technology use. It would drive me nuts.

No more. After considering the events around and surrounding what I wrote about starting with the basics, it dawned on me that the culture, at least for the last decades, demanded making it’s own mistakes. The winning bidder in technology is generally something that was marketed to the government, or which requires an allegiance to the software manufacturer in Redmond, Washington, all the while complaining about the United States.
For me, it seems technology usage lags by about 20 years behind the United States, which is becoming very awkward with the new technologies coming out faster than the crippling bureaucracy of Trinidad and Tobago can adapt – and when they adapt, it’s without learning the lessons of the last 20 years in other countries. That’s a very negative thing to write, but all too often it’s true.

Technology, though, can’t exist in a vacuum. Technology can only serve those who know how to operate it, or they get burned. Listening to a conversation today in a coffee shop, where an apparent meeting was taking place to sell tech adaptation services or something along those lines, the guy in running shorts with ear buds in was explaining to the professionally attired woman that he had saved the world with technology at other companies, and thus he knew what he was talking about.

I chuckled even though their loud conversation was annoying while I was reading because I’d see those guys for at least 3 decades sell themselves as solutions. People then buy the solutions, and then complain about the solutions, then want to fix the solutions because nobody wants to admit bad money was spent, even in a committee… until eventually they get someone who actually has some experience but they’re too broke to pay. There was a part of me that just wanted to look at them and say in a very level voice, “That’s a bunch of bullshit”, but then I remembered something very important.

It’s part of the process, and I may have been underestimating that woman’s bullshit sensor and that’s what needs to evolve. The bullshit sensor, and perhaps the bullshit feedback mechanism. Bypassing that is dangerous, and it’s a necessary part of technology growth. In fact, I’d offer that there’s quite a bit of that bovine fecal matter stuck in the cogs of bureaucracy from various fields beyond technology.

So I sat and finished my coffee, reading my book, satisfied that the process was underway, and that bullshit sensors would self-adjust or deprecate. I had no part of it and that made my day brighter.