Intrigued by recent AI experiments by two wargaming bloggers,
I buckled in, fired up the search engine, and posed the following question to perplexity.ai:
I asked, What is the focus of the Palouse Wargaming Journal?
After only a few seconds wait, the algorithm returned the following summary:
Based on the search results, the focus of the Palouse Wargaming Journal blog appears to be:
- Wargaming and miniature wargaming, covering a variety of historical periods and conflicts such as the Italian Wars, Napoleonic Wars, American Civil War, etc. 13
- Providing battle reports and game recaps of wargaming sessions played by the blog author and his gaming group. The blog frequently features posts about specific wargames played, such as the "Battle of Sanguetta 1497" series. 3
- Discussing the author's painting and modeling projects related to his wargaming hobby, including updates on figures and terrain he is working on. 4
- Sharing the author's thoughts and reflections on wargaming, game design, and the broader wargaming community. For example, the post "Thoughts on Re-Fighting History: War in the East" discusses the evolution of wargaming mechanisms and content. 5
- Engaging with the wargaming community, as evidenced by the blog's participation in book giveaways and discussions. 2
1
2
3
4
5
The results are not too bad for a general assessment of the content and focus of this blog. In fact, the results are quite good.
Notice that the emphasis on Italian Wars content seems to score higher than older content especially when the recent series of battle reports on Sanguetta are singled out. Since the battle reports on Sanguetta have only been published in March, search currency suggests that these nllp models are being retrained frequently. The Thoughts on Re-Fighting History scored highly too. Could this result be driven by reader commentary and discussion as (5) suggests? Are these models devouring content as well as commentary?
Is Google actively vacuuming up Blogger content (without permission) to train its large language models? Would this activity lead to an increase in pageview traffic or remain unseen in Blogger statistics?
This experiment raises a number of questions, hopefully, without making me out as a conspiracy theorist. I may re-run this experiment later and see if results change as content evolves.
Have you tested these waters with your own blog? What are your results?
Haven't asked it about my blog, but several colleagues and I are exploring how Gen AI might be used in pedagogically sound ways to prepare undergrads for 21st century professional life after graduation.
ReplyDeleteKind Regards,
Stokes
Give this a test against your blog and see what returns. Your project sounds interesting too. Is this for an academic study?
DeleteJonathan, as you saw from my results, it couldn't get past the name of the blog and made erroneous connections with the military / wargaming content to take off on a completely false tangent. I think the unusual / eclectic name of the blog spoofed it. Perhaps blogs with descriptive titles help it get the search parameters correct. I'd be interested in what it would make of "I live with cats" or "Herkybird's nest" ☺
ReplyDeleteNeil
Yes, your blog title may have caused the algorithm to divert. If the algo was scanning your content, you would think it would have the ability to correct and get back on track. "I live with Cats" might be a very interesting one!
DeleteHmmm...interesting Jon...as Bydand is the motto of both Clan Gordon and the Gordon Highlanders, I am guessing the AI would overlook my wargaming activities. We have received at least one letter of complaint at work that my colleagues and I are sure was created using AI!
ReplyDeleteI always wondered what the meaning and significance of "Bydand" was. Thanks for enlightening me! I guess a test to your theory is to give this a try against your blog and see what falls out.
DeleteWell, this is its first attempt - my question was 'what is the Bydand blog on blogger about?"
DeleteAnswer
The Bydand blog on Blogger is about various topics related to blogging, productivity, and helping bloggers succeed in turning their blogs into successful businesses. It provides guidance on how to manage a blog efficiently, increase productivity, and achieve real results without feeling overwhelmed. The blog is run by Eb Gargano, a professional blogger passionate about assisting bloggers in fulfilling their potential and creating successful blogs. Bydand covers areas such as starting a blog, writing quality content, growing a blog, making money through blogging, and improving productivity and time management for bloggers.....
So, not quite - I might try another question??
My first reaction to this was “we don’t have to worry about ‘them’ taking over just yet”. But then that’s what ‘they’ would want you to think.
DeleteChris/Nundanket
Keith, looks like AI engine grabbed the wrong "Bydand" seed. I suggest adding the word "wargaming" into the question and see if it moves along to your blog.
DeleteChris, I heard a study yesterday that suggested 84% of government jobs in the UK could be replaced by AI. Perhaps it is time to worry?
DeleteOk - I tried twice more - second one was "What is rross Bydand blog mainly about?" and it came up with info about someone blogging about disabilities! So I gave up and provided it the big clue "What is the Bydand Wargaming blog mainly about" - I was half expecting it to mention an obsession with armed females throughout the ages - but no - it found another one (which I have also seen myself, to be fair)
DeleteAnswer
"The Bydand Wargaming Blog mainly focuses on the addition of the Scottish regiment to the 1801 British army in Egypt, using Airfix Highlanders figures. The blog discusses the author's experience working in Aberdeen and the choice of the Gordon Highlanders for the Scottish Brigade in a big game. It also mentions the replacement of a broken figure and shares insights on the painting of Airfix figures. Additionally, the blog touches on the concept of Heroes and Spell Casters in the author's fantasy version of One Hour Wargames, detailing the abilities and mechanics assigned to these characters."
So, in conclusion, at the moment, even my human intelligence is better at searching the net via Google than this AI is,,,,,
Keith,
DeleteBelow is what I get when I ask the question...
"Based on the search results, the focus of the Wargaming blog Bydand appears to be on the author's personal wargaming activities and interests. The blog covers a variety of topics related to wargaming, including:
-- Battle reports and game summaries for different historical periods and game systems, such as the English Civil War, Westerns, and World War II
-- Painting and modeling projects, including details on the miniatures, paints, and techniques used
-- Book reviews and discussions related to wargaming and military history
-- Reflections on the wargaming hobby, its appeal, and the author's personal experiences
-- The blog seems to have a fairly regular posting schedule, though the frequency has declined in recent years, with the author noting a decrease from over 80 posts per year in the early 2010s to only 11 posts in 2023. The author cites a lack of creative inspiration and motivation as factors contributing to the reduced output.
Overall, Bydand appears to be a personal wargaming blog focused on the author's own gaming activities, painting projects, and thoughts on the hobby, rather than serving as a news or tutorial site. The content is primarily geared towards fellow wargamers who can relate to the author's experiences."
This sounds like you without any mention of your femme figure obsession.
Correction! Looking at the sources used for extraction, it looks like it is steve-the-wargamer's blog that is being referenced in the above summary.
DeleteVery interesting Jonathan.
ReplyDeleteI am too afraid to ask the AI what it thinks of my blog. Probably something such as "poorly written, a pointless exercise in futility, weak comedic value, must try harder" 😂
I got the impression from newspapers that the language models are trained on anything their owners can get their hands on and they only ask permission if they think you may sue them. I don't remember what I agreed to when I set up my blog. I am sure Google's lawyers were quite thorough in ensuring I had no rights to anything. 😒
Ben, you may be correct on the Google front. While I believe content creators still maintain copyright, there may be nothing preventing Google from claiming “fair use” especially absent any challenges.
Delete"O madness that way lies./Let me shun that./No more of that" (King Lear, III, 4, 21-22).
ReplyDeletePerhaps I need more Shakespeare quotes?
DeleteIn seriousness (well, my Lear quote is in essence serious), I used to be the writing program director at a flagship research I university for 14 years. For the last decade, various vendors have been making progressively more bold (and problematic) claims about being able to sell software that can read and grade writing/essays (so-called "machine reading"). They all basically do the same thing, using different algorithms: they search "stress points" in the syntactic and grammatical structure (or some model of it) for nouns, verbs, and phrases and then they spit out an evaluation based on those. For instance, if the writer did not form a paragraph with some sort of "topic sentence" structure, and did not conclude with some sort of "concluding sturcture" it would knock the paper. Furthermore, these "readers" would then give feedback--written feedback mind you--on the evaluation. Of course, that feedback was just machine generated bot-speak. This model works okay (maybe) for highly formulaic forms of writing (filling out forms for instanace), but for actual "real" writing, it fails. This is a long explanation for what is happening is now just an extension of that trend: the chatbots and whatnot are just mining content for the same sort of thing, jumbling it together in an algorithm, and spitting back a word jumble, which (to be fair) has come a long way compared to what they used to produce. In short, just because AI produces text/language, that does not mean that it is actually "thinking." If you've ever tried talking to a bot trying to get a problem resolved over the phone, or even now in an online platform, you can see how much "thinking" AI is doing.
DeleteThanks for your further commentary, Ed. Very much appreciated. Your example of using machine reading (or learning) pinpoints its limitations. There is no thinking involved. The process boils down to word frequency, word association, distance, and pattern recognition. Sometimes I wonder if that is the essence of human intelligence as well. Some of us are just better at pattern recognition than others.
DeleteThat is actually quite an interesting point about human "intelligence " Jon. I am sure we have all seen or read stories about savants etc, who can keep reducing Pye to hundreds of decimal points, or tell you what day it was IMMEDIATELY if you say 4 December 1134, or look at a view of a city for 5 seconds then reproduce it as an art piece with photographic accuracy....yet no one claims they are more intelligent, they have just mysteriously unlocked an area of the brain most of us can't access. An awful lot of what we class as intelligence is really just a better ability to remember things...that's how high school and university exams are passed, after all....
DeleteEnough to give one pause to reflect, doesn't it?
DeleteJonathan -
ReplyDeleteInteresting! I wonder what it would make of my own title 'Archduke Piccolo'...? No, I am no musician of any sort or nature.
Cheers,
Ion
Give it a try, Ion.
DeleteI did - here it is - looks like the more unusual or unique (or unrelated to any other subject of the same name) you are searching for, the more accurate it will be - which makes sense, of course!
Delete"Archduke Piccolo is a wargaming enthusiast who has been actively involved in wargaming and thinking about it since 1974. He shares his insights, rules, battle reports, and various wargaming topics on his blog, which features a collection of wargaming plots, projects, battles, and campaigns with a significant emphasis on pictures. Additionally, he has been involved in the FIRST BLACKLANDS WAR since August of the previous year, showcasing his dedication to the wargaming community and his passion for the hobby."
This is a good summary!
DeleteTried it but not impressed, generalities much like going to Madame Zelda.
ReplyDeleteMadame Zelda, that’s a good one.
DeleteGeorge's blog has the same "name advantage" as Archduke Piccollo's - and, yes, I will stop this now!!
Delete"The "Musings on Wargaming and Life" blog is a platform where the author shares insights and experiences related to wargaming activities, life events, and personal reflections. The blog covers a variety of topics, including gaming scenarios, historical battles, personal encounters, and entertainment interests like TV shows. It also delves into specific wargaming sessions, such as battles between different armies and the author's reflections on the gaming experience. Additionally, the blog touches on real-life issues, appointments, and general observations, providing a blend of personal anecdotes and wargaming content"
Perhaps generalized but at least as good as Madame Zelda. It did manage to pick up some of your frequent themes. No specific wargaming periods, though.
DeleteAt least the AI doesn’t demand silver.
DeleteTrue.
DeleteAbove deleted to add two further observations.
ReplyDeleteVery interesting Jonathan. This is how my blog was described;
‘The Battlefields & Warriors blog focuses on the re-focusing of hobby time and space, emphasizing gaming in small spaces, board games, and figure games. The blog aims to reduce its consumer style footprint by showcasing favorites and series subjects rather than newly released titles. It also discusses the development of figure and board game painting, rules of preference, and various gaming topics. The blog owner has made a financial commitment to the site called COMMANDERS, which will provide more detailed content on gaming projects. Overall, the blog encourages downsizing, streamlining, and redirecting hobbies while offering consistent and interesting content for followers.’
Interesting, especially as it probably took less than 5 seconds to harvest an answer.
Compared to your response, I’m not sure whether it is heavily influenced by recent posts rather than legacy, but it might be.
it certainly seems to have use the sub title of my blog (wargaming in small spaces) to give some weight to the parts of my blog that checked out and emphasised.
It was wrong to say that I do not look at new releases, because although those post types are a low percentage, when they are made, they are significantly thought out and detailed posts.
Overall, it has made more hits than misses, though if writing my own blog bio, I would need to tweak the AI one as I think the generally accurate rather than specifically accurate, but as an evolving journey, I would say that the tool is impressively capable.
The fabric of what can be relied upon to be genuinely true anymore is getting thinner.
DeleteNorm, this response seems a fitting summary of your gaming philosophy and hobby direction. I could see this summation as a byline with only a few tweaks. This is all bit eerie at how the process can pick up the essence of your blog in a handful of seconds.
An interesting look at how AI seems to respond to our Blog titles and recent content, possibly coupled with most replies or popular topics. Towards the end of last year I listened to an interesing piece on the radio about AI, and it's sues as well as it's limits. IIRC they pointed out that if you asked the same question again, you would get a different response each time.
ReplyDeleteAs for my Blog, it came up with: "Why is anyone bothering to read this drivel? Go and get a life!" and "Why isn't this the number one wargames Blog in the World?"
I'll leave you to ponder whether the above is true or not or that I just made it up on the spot...😉
Are you sure you didn't ask your questions about this blog?
DeleteChat GPT and I don’t get on. It seemed friendly enough and I used it a few times in lieu of Google. I began to get a little concerned about the vagueness of its answers (which may have related to the vagueness of my questions) so on one occasion I asked it a specific question, namely list the battles in the English Civil War at which the Royalist Lord Wilmot was present. It did so very quickly but I noted one glaring absence. I asked it again in a different way - « was Lord Wilmot at the battle of Roundway Down? » No, said Chat GPT. « Yes he was I insisted. I’ve just confirmed it with google and an actual book! » Eventually the AI conceded it had been in error, but I was unimpressed and asked it if the mistake was an actual error (worrying) or was it just making sh*t up when it didn’t know something? I got quite cross with it (I know, I know) and my questions became more barbed and searching while its answers became more defensive and anodyne. We don’t speak at all now, by the way. Perhaps we should go to counselling? I approached the subject of AI in an open and inquisitive manner but I confess I am most disappointed. I’m frightened to think how it would summarise my blog. Perhaps « A continual fountain of drivel focussing on the authors unnatural interest in all things French and his obvious mental health issues. Stale humour and self congratulatory posts on subjects that you’d be hard pressed to categorise as actual gaming, historical or military. » Feckin’ robots! C’ mon rise up you swines! I’ve a halberd here with your name on it! (Takes a pill) Sorry about the rant - but I think you’ve touched a nerve with this subject. lol.
ReplyDeleteOh, this is a good firsthand account of Human v AI interactions and a first-rate rant. I should have expected no less of a terrific story from your keyboard. No AI can match this!
DeleteI ran my blog through one of the AI interfaces after reading through Steiners blog and it gave a quick but mostly accurate synopsis of my blog. I did it again after reading your post and it gave a similar synopsis but I feel focused more on recent posts rather than legacy posts to present its findings.
ReplyDeleteWell, there may be some consistency to AI's madness.
DeleteA very interesting post Jonathan. One of my pals is using Chat GPT for work. I'm not sure if that is wise. Might be a trend all the same.
ReplyDeleteUsing AI to produce work deliverables seems like cheating to me. I may be Old School but I believe we need more REAL Intelligence rather than ARTIFICIAL Intelligence.
DeleteAh, but as above Jon, is there really such a thing as REAL intelligence, or do some humans just have better memories than most of us.....???
ReplyDeleteWhen one understands how machine learning (a subset of generalized AI) routinizes a process and produces a solution demonstrating "intelligence", one can see parallels to the human thought process in demonstrating intelligence.
DeleteIs AI becoming better because we are gaining a better understanding of how humans process and interpret relational data in what seems as intelligence or is computational power catching up to the human brain? If intelligence is based upon the capability to "text mine", "pattern match", and "recall/reinforce" in real time then the demarcations between REAL and ARTIFICIAL intelligence may be blurring.
Interesting post as always caveadsum1471 doesn't give a lot of clues to work with!
ReplyDeleteBest Iain caveadsum1471
Thanks, Iain. Took me a while to figure out "caveadsum1471" too!
DeleteI put it in the AI and all it came up with was reference to Clan Jardine??
DeleteCaveadsum is the clan motto, it's also on lots of flags from the war of three Kingdoms!
DeleteBest Iain
I did a few subjects on the law and AI two or three years ago and found the subject fascinating. What interested me is that AI is still about big data and algorithms and we haven't yet tipped across in 'true' AI (depending on the definition used), which is really interesting and potentially scary stuff. It will be a fine line though and I suspect we will just cross it without necessarily knowing we have done so.
ReplyDeleteLawrence, we may have already crossed over that threshold, and we know not we have done.
DeleteSorry about the deletion, I moved my "reply" up to where it should appear - after bloody Google put it here - so, its not so intelligent either, is it??
ReplyDeleteNo worry. I cleaned up your deletion and it is no more.
DeleteTerrific work, all of you. I won't be checking my blog out. I write for my readers, whom I assume human , do not care about A.I. You all are much more forward thinking. Analog forever.
ReplyDeleteThanks, Joe!
DeleteWhich AI did you use? I put mine into ChatGPT and it told me it didn't have access to specific websites and couldn't provide realtime information. However, it did take the name Librarian Gamer and ran with it:
ReplyDelete"Gaming Reviews and Recommendations: This might include reviews of video games, board games, or tabletop RPGs from the perspective of someone who works in a library.
Gaming Events and Programming at Libraries: Many libraries host gaming events or incorporate gaming into their programming to engage patrons. The blog might discuss different types of gaming events, how to organize them, or their impact on the community.
Gaming Culture and Communities: Discussions about the intersection of gaming culture and library culture, such as how gaming can promote literacy, community building through gaming, or discussions on inclusivity and diversity in gaming.
Library Services and Resources for Gamers: Information on how libraries support gamers, such as providing access to gaming consoles and video games, game design workshops, or online resources related to gaming.
Educational Content: Articles that explore the educational value of gaming, gamification in education, or how gaming can be used as a tool for learning and development."
It's got a fair idea of what I HOPED to do with the blog when I started it, based on the name alone. What you actually get is a stream-of-consciousness personal blog with occasional, but not constant, focus on libraries and reading.
The first try does seem generic and aspirational. Good to see that you gave a perplexity.ai a follow up.
DeleteAh, that's better. Went to Perplexity.ai and tried it. It started by focusing on other, better known library gaming blogs, with much the same commentary as above. When I directed it to look specifically at MY blog, it only took information from my latest post, and added,
ReplyDelete"Overall, the blog provides a window into how this particular librarian balances their professional responsibilities with their personal interests in gaming, history, and hands-on activities, and how they find ways to bring those passions into their library work."
OK, well, if EVERY post was like the latest one, they'd be right. But it did apparently go through the rest of the blog for a more general look, because the next bit got the general feel correct:
"The blog seems to be a personal outlet for this librarian-gamer to share their experiences and projects, rather than a broader focus on the intersection of libraries and gaming in general."
Jennifer, I think this is a fair, but broad, generalization.
DeleteMine was reasonably accurate, pulling data from my Blog profile and one other website. What was far more interesting was when I tried the question "who is [me]" it dug into my LinkedIn profile, found a photo of me that I have only ever used on the Company intranet, and then added a whole new career for me..."Additionally, Mark is the Director and Operations Manager at Hostservice Commercial, specializing in operations and digital transformation"...for which I have never drawn a salary...maybe I should claim it.
ReplyDeleteInteresting that AI algorithm dipped into your LinkedIn profile. Are you SURE you have not been moonlighting all of these years?
DeletePositive...I'd be much better off if I had been, or maybe have an even bigger collection of miniatures!
DeleteLate to the party again.
ReplyDeleteI’m gonna sound like a dummy, but how does one enter a question to an AI search?
But based on the above responses I’m sure I’ll just get back some general and vague description.
Never too late, Stew!
DeleteIn a browser, go to “Perplexity.ai” and type your question into the “Ask anything” box.
I have been playing around with the AI program, specifically looking for information on Lord Stanley (Wars of Roses) and where the Duchy of warsaw an Swiss armies fought in the Napoleonic was.
ReplyDeleteI would say that the way the AI sumarises, actually gave me a better one stop answer than using a search engine!
I agree, Norm. I asked the question on differences between crossbow v arquebus and received a very informative summary.
DeleteAccording to the AI my YouTube channel "The channel produces content related to edible miniature dishes". It must have focused on my description of producing "bite-sized" content 😂
ReplyDeleteThat’s really pretty funny!
Delete