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.

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.

Roger Edwards
Writer & editor of Contains Moderate Peril. A website about gaming, genre movies & cult TV. Co-host of the Burton & Scrooge podcast.
http://containsmoderateperil.com
Next
Next

LOTRO: Project Questa