Technology, AI, ChatGPT, AI Images, Google Analytics Roger Edwards Technology, AI, ChatGPT, AI Images, Google Analytics Roger Edwards

Experimenting With AI Part 2

Going forward, if I write any more posts about my use of AI, I am not going to add the following caveat. I will do it once more here, so everyone knows where we all stand. I am fully aware that AI has already taken jobs and will continue to do so. I also know that data centres are not environmentally friendly. As for the evil corporate billionaires that get rich from the situation, that also has not come as a surprise to me. I also believe that the AI market needs regulating and there should be legislation in place to ensure that AI is never directly linked to important government and civil infrastructure. That being said, I am not going to stop using AI at a domestic level over notions of ethical purity. All of the above criticisms can broadly be applied to the industrial revolution and society came to terms with that and survived it. The same goes for the computer revolution. Things change and we adapt. Plus, if you really wanted to protest and lobby against AI, the best time to do this was two decades ago.

Going forward, if I write any more posts about my use of AI, I am not going to add the following caveat. I will do it once more here, so everyone knows where we all stand. I am fully aware that AI has already taken jobs and will continue to do so. I also know that data centres are not environmentally friendly. As for the evil corporate billionaires that get rich from the situation, that also has not come as a surprise to me. I also believe that the AI market needs regulating and there should be legislation in place to ensure that AI is never directly linked to important government and civil infrastructure. That being said, I am not going to stop using AI at a domestic level over notions of ethical purity. All of the above criticisms can broadly be applied to the industrial revolution and society came to terms with that and survived it. The same goes for the computer revolution. Things change and we adapt. Plus, if you really wanted to protest and lobby against AI, the best time to do this was two decades ago.

Moving on, at the beginning of July, I wrote about experimenting with AI. I had recently stopped subscribing to Google Gemini and had started using ChatGPT Plus. I mainly use AI for research, learning specific skills, assisting me with areas that are not in my skills set and augmenting images. The latter sounds dubious but it usually just entails altering an image to make it 16:9 and that process requires altering minor elements. As a tool, I find ChatGPT invaluable and I especially like the option for voice interaction. I have this installed on my phone and I use it mainly for information when I’m out and about. I was recently travelling to Rochester by train and there was some confusion over the timetable. A quick spoken enquiry into my phone yielded a comprehensive verbal answer, along with the same response in text. As I said, invaluable. I always advocate “use the right tool for the job”. AI is now, for good or for bad, part of my regular toolkit.

Although my experience and use of AI has been mainly positive, there have been a couple of occasions when I have run into some curious foibles. The first, although annoying at the time, was the result of a well intentioned policy, although poorly implemented. I was planning a review of the classic Dennis Wheatley novel, The Devil Rides Out. I found a montage of several of the paperback book covers from the sixties and seventies reprints. However, the book covers in the picture were somewhat worn and I want the image restored, enhanced and enlarged to a suitable size. So I duly asked ChatGPT to do this. Something it had done for me before several times. Not so on this occasion. I was politely informed that “We’re so sorry, but the image we created may violate our guardrails around nudity, sexuality, or erotic content. If you think we got it wrong, please retry or edit your prompt”. Judge for yourself if you think the source material is especially salacious. This decision made me chuckle.

The second one happened earlier today. Google Analytics has now added a chat facility to their popular website stats package. I don’t particularly like the service because it doesn’t use the terminology that I’m familiar with and frankly none of the data displayed about this blog’s internet traffic, correlates with that produced by Squarespace themselves. I pretty much said that in the chat window today and then ended with a Dickensian flurry of “Good day to you, Sir”. I also stated that if their stats were correct (which I do not believe they are) I may as well quit blogging after 19 years. Only to be met with a very earnest response of “Please don't give up on your website based on these numbers. Digital analytics is currently in a state of transition due to global privacy changes, which has made tools like GA4 harder to use and their data harder to compare”. Apparently AI have a hard time recognising sarcasm but bravo for being concerned about me giving up on my hopes and dreams. I felt like saying “you’re right. Let’s put on the show right here”.

I’ll make no bones about it, I enjoy my interactions with ChatGPT. It’s been designed to make me feel this way. I’ve stated in my prompts that I don’t want flattery or my ego massaged and I find the response that I now get are pitched at exactly the right level. Like most people who interact with things that aren’t human, I have to fight the urge to lapse into anthropomorphism. Yet because of my upbringing, I still say please and thank you the ChatGPT. I do have sufficient scepticism to limit what it can access on my PC. I don’t trust its corporate masters. But I genuinely do like our collaboration when problem solving. It is thorough, procedural and documents things very well. Attributes I relate to. It also doesn’t claim to know everything and can be genuinely surprised by my contributions. I also greatly appreciate how you can pick up a line of enquiry hours or days later and just continue. Hence my AI experiment continues and frankly its a lot of fun.

Read More

Experimenting With AI

For the last few months I have being using Google Gemini. I subscribed so I could access a wider spectrum of services and evaluate it effectively. I also wanted to dispel some of the hysteria that accompanies any conversation about Large Language Models and Artificial Intelligence. The results were initially interesting and Google Gemini proved useful when researching material for blog posts. It is good at providing summaries about well documented subjects. I wrote a post about food banks recently and it distilled a lot of data into a manageable amount, which was ideal for my article. Google Gemini has also produced some visual basic scripting and simple batch files that have allowed me to automate processes on my PC. Such as changing the default monitor, or screen resolution at the click of an icon. However, I found this AI struggled with in-depth software troubleshooting and that its ability to create images varies greatly depending on the subject.

For the last few months I have being using Google Gemini. I subscribed so I could access a wider spectrum of services and evaluate it effectively. I also wanted to dispel some of the hysteria that accompanies any conversation about Large Language Models and Artificial Intelligence. The results were initially interesting and Google Gemini proved useful when researching material for blog posts. It is good at providing summaries about well documented subjects. I wrote a post about food banks recently and it distilled a lot of data into a manageable amount, which was ideal for my article. Google Gemini has also produced some visual basic scripting and simple batch files that have allowed me to automate processes on my PC. Such as changing the default monitor, or screen resolution at the click of an icon. However, I found this AI struggled with in-depth software troubleshooting and that its ability to create images varies greatly depending on the subject.

The first major adjustment I had to make while using Google Gemini is that I needed to be very specific in how I phrased my question. Google Gemini is not intuitive and doesn’t always proactively ask you for additional data. It will take the prompt provided and doggedly work within its confines. You then realise that it needs more information and thus end up micromanaging the process, as it attempts to solve your problem. It would get to the right solution eventually but the amount of time and effort I would have to make with my continuous interventions and data updates, some what took the shine off the end results. This became very apparent when I tried to finally solve a long term problem regarding intermittent connectivity issues between my PC and Fire HD10 tablet, when using a USB cable. Appraising me of the failings of Microsoft Media Transfer Protocol without giving any useful suggestions within the parameters I’ve asked isn’t helpful.

A rather generic fantasy image depicting Ecthelion Versus Gothmog, created via Google Gemini

Another issue that quickly became noticeable was that of image generation and the disparity in quality between specific types. On one occasion I asked Google Gemini to create an image specifically for a blog post, because I couldn’t find a comparable one online. I wanted a picture of a group of demonstrators outside parliament talking to a news reporter and crew. I eventually gave a detailed prompt and found this replication of a common place event to be satisfactory. However, when I gave detailed instructions for a fantasy based image, I found the results to be somewhat formulaic and lacklustre. Google Gemini seems to work best when drawing from established data and images. When called upon to do something inherently creative it doesn’t fare so well. Furthermore, if you draw attention to any mistake or confusion arising from your interactions with Google Gemini, the AI becomes excessively apologetic to the point of obsequiousness.

It was ultimately this lack of intuition and proactivity that made me cancel my subscription to Google Gemini. Using it was too labour intensive and required me to constantly oversee the proceedings. For me that mitigated some of the benefits inherent in using such a tool. Hence I moved on to ChatGPT and decided to proactively determine if it had the same failings as it competitor. I asked it whether it felt it was intuitive and likely to seek clarification on its own accord rather than just colour “within the lines”. It confidently stated that it was a more intuitive by default and immediately proved so when I set it the same problem that Google Gemini had laboured over to no avail. ChatGPT not only solved the problem with my tablet but gave me multiple solutions. It also displays its thinking process as it works through a problem, which is both useful and intriguing. Its creative artwork is superior, or has at least proven so for the present.

A map of Númenor created via ChatGPT

AI in various shapes and forms is a reality that is no going to go away. That being said, I do not think it is the universal solution that many think that it is at present and I suspect that there will be several high profile failures in the months to come that will do much to reset both business and the public’s expectations. Sadly, I also think there will have to be an adjustment around the wider issue of those who directly affected by the use of AI. If I ever have to commission any further design work for my website or the branding associated with it, I will always hire a professional. However, for minor work, AI will suffice. For example I wanted a detailed, high resolution map of Númenor and gave the task to ChatGPT. The results were fine. However, this never was a paying job to begin with. A few years ago, before AI became commonly available, I would have just gone without or drawn it myself. The fact that a tool now exists to do it for me, means I will use it.

Read More