Introduction
If you are reading this post long after its March 2025 publication date, you might become puzzled at its many failings until you realize, “Oh, wait, this was written back when Dana wrote his own blog posts instead of assigning them to GPT-28-turbo-XL-prime! The lameness is because he did his own very light research instead of basing his observations on the entire body of knowledge of the Internet, and because it’s a plebian human voice instead of an infinitely exalted and witty A.I.!”
I have now blogged 14 times about A.I. and its evolution. My last ChatGPT check-in was about three months ago. The A.I. version hasn’t changed since then; as of this writing it’s still GPT-4-turbo. But what has changed is the range of tasks I’ve experimented with. I now realize my previous posts failed to appreciate some of the things ChatGPT does really well. This post showcases those, while also providing commentary on what the A.I. still does not excel at (and likely never will). You’ll also learn more about why you may have seen an annoying banner about cookies at the top of this blog.
Caveat
This post is mostly about ChatGPT though it touches on Google Gemini. What it doesn’t cover is the “Visual Look Up” feature on Apple’s iOS platform that leverages “Siri Knowledge.” I don’t currently own any Apple products (except an iPod mini in a drawer somewhere) so all I know about Siri is that it did a comically poor job of identifying the breed of my brother’s cat today, based on this snapshot he sent me:
How an A.I. could think any image looks like both a cougar and a wallaby is beyond me. I’m going to assume Apple is so far behind in the arms race that we can simply ignore it for now.
Real-world problem solving with GPT-4-turbo
Until recently I’d only messed around with GPT-4 for the purpose of evaluating it (and, whenever possible, mocking it). But then I hit upon a real-world use case and dove back in. My motivation, which I’m sure you’ll relate to, was: HOT CASH MONEY. Who wouldn’t want this, other than those tedious killjoys who spout aphorisms like “Money is the root of all evil”?
By way of background, I’d noticed that the albertnet page view count had soared in recent months. It took this blog something like 14 years to reach a million page views, but in the last six months alone I’ve now seen almost 1.4 million more. But then, isn’t this how the Internet works? Moore’s Law? Nielsen’s Law? All that compounding magic? In the whole time I’ve had this blog I never even considered monetizing it through ads, but every man has his price. (I’m not sure exactly what mine is, but I reckon I’ll know it when I see it.)
Driven mad with money-lust like one of the guys in “Treasure of the Sierra Madre,” I needed answers—fast. So I asked GPT-4-turbo, “My blog, www.albertnet.us, has received 1.2 page views in the last three months and traffic is increasing. If I turned on Adsense, approximately how much money would I earn per month?”
Yes, “1.2 page views” is a typo, but I didn’t make it here … that’s actually what I asked ChatGPT. It replied, “What the hell do you mean 1.2 page views? How do you have 2/10 of a page view? Did some user barely see the screen, like out of his peripheral vision? Or are you just whacked out on coke and smack and typed your query wrong?”
Okay, you got me … that’s not at all how GPT replied, though honestly I think that would be the better answer. What it actually provided was a lengthy essay, full of data points and computations, answering this useless question. My favorite part of the response was, “Number of Page Views (Traffic) – You’ve mentioned you have 1.2 page views in the last three months, which is approximately 400 page views per month (assuming the traffic is consistent).”
Huh? How do you get 400 by dividing 1.2 by 3? I guess the chatbot arbitrarily assumed the figure I provided was in thousands. That’s a pretty big logical leap, and GPT didn’t document the fact of this assumption. It then proceeded to run a bunch of calculations based on 1,200 views, the punch line being that I could make about $2/month. So the more succinct answer would have been, “Dream on, bloggy-boy.”
When I corrected my original query to 1.2 million page views, GPT-4-turbo reran its calculations and informed me that I might expect to earn something in the neighborhood of $2,000/month in passive income. Now we’re talking! It did suggest a number of caveats, such as how my results might be affected by the geographical location of my readers, the positioning and type of ads, ad targeting, how well ads match my content, user engagement, and so on. I asked it a bunch more questions specific to Adsense, whether GPT’s estimated click-thru rate (CTR) assumption is realistic, etc. While it provided all kinds of useful info, it missed one very important rule of thumb: if something seems too good to be true, it probably is.
I mean, come on … albertnet is a blog about nothing. I’m not going on political rants that cause trolls to leave endless acerbic comments and then forward my post to 90 friends with an exasperated preface like “can you believe this shit?!?!!?!” If all it took to create a nice passive income stream was to blog every single week for 15 years straight so that after more than 3,500 hours of writing you’ve amassed over 750 posts, comprising over 2 million (juicy, searchable) words, then everybody would be getting into this business, obviously. If quality, rather than nudity, attracted people’s attention, every liberal arts grad on the planet would be driving a Benz. (Well, except for me, because regardless of my income—actual, theoretical, or pipe-dreamed—I will always be the world’s cheapest man driving a used Volvo.)
I feel really bad for the earnest blogger who sees all this traffic growth, does a basic ChatGPT query, thinks he can trust the response, and makes a lot of effort adding ads to his blog to harness this new fountain of riches. I hope nobody is that naïve. Since I’m not, my first impulse was to get a second opinion. So I put my query to Google Gemini, without the typo this time, and it gave me a very similar answer: I could make right around $2K a month, just for setting up Adsense and then sitting on my ass!
This seems like the kind of claim I’d get from a spammer. In fact, I’m going to check my spam right now to look for this kind of hoax. Hmm, that’s odd. Though 22 of my 50 spam messages are from recruiters, none is this specific. I do, however, have a message from “Super-size” titled, “Now imagine each night, having 5 or 10 concubines around you, each one craving your masculine essence in them. #632352.” This subject line is interspersed with various emoji including, oddly enough, an avocado. Is avocado a concubine’s favorite food? Let me ask ChatGPT. Okay, it replied in the negative, pointing out that concubines were prominent “in ancient or medieval times, when avocados were not available in their regions.” I think the innuendo of “in their regions” was accidental. (And now I’ve realized how long and pointless a digression this has been. I’m tempted to apologize, except this might end up being my favorite paragraph of this entire post.)
The caveat GPT-4-turbo should have provided is, “My calculated revenue assumes the page views are from actual readers, not bots.” The idea of bots grossly polluting my page view stats was my natural assumption, but not one GPT addressed. I think this is an important object lesson: it doesn’t matter how useful A.I.’s responses are if you don’t know to ask the right question. Perhaps A.I. will advance to the point that it would not only sanity-check my page view stats, but would be the one to keep an eye on my blog traffic to watch out for moneymaking opportunities in my stead. (If and only if it knew albertnet to be an amazing viral sensation for reals.)
Where ChatGPT shines
After feeding me all that false hope, ChatGPT asked if I’d like help setting up Adsense on my blog. I decided instead to enlist its support vetting the quality of the page view stats. Having drilled down a bit on my own (which Blogger doesn’t make super easy, by the way), I discovered that page views from France were 12% of my total over the last six months, 14% over the last three months, and 39% over the last 30 days. I shared this with the chatbot and queried, “Is there A.I.-driven or bot type traffic that would originate in France that could artificially inflate the metrics around my readership?” (I now regret the specificity of this, as I was clearly “leading the witness.”)
ChatGPT responded with a clear and detailed essay about the probable causes, including “Bot Traffic (Most Likely Explanation).” It filled me in about scrapers and SEO crawlers and A.I. training bots, and suggested I use Google Analytics to investigate further. This ended up being an excellent suggestion and led to my most engaged use of GPT ever.
First I quizzed the chatbot about whether Google Analytics has a free version (it does), whether I’m giving up any privacy (basically not), etc. Then I set up Google Analytics (aka GA4), which was pretty straightforward, except I noticed in the Terms of Service that I’m expected to comply with GDPR (the EU General Data Protection Regulation) when gathering this detailed user data. I happen to know what GDPR is, so I asked GPT all about it, in terms of what I’m really expected to do to comply. It turns out that compliance is a royal pain in the arse (my words, not ChatGPT’s). Since I do get readers from Europe (whether it’s 39% of all traffic or not), I need to have a publicly posted privacy policy and a banner announcing my use of cookies (which is how GA4 can track usage). I almost abandoned the whole project, on the mere assumption that my page view stats are so obviously bogus I don’t need to expend all this effort verifying it, but then … what if these traffic stats aren’t bogus? What if I really could just sit back and rake in money? Isn’t it worth spending some time and effort investigating the possibility?
I asked GPT for some nice boilerplate text for the privacy policy, and though much if its response was unusable, some of it was good, and if nothing else this rough draft prevented writer’s block and paved the way for my policy, which you can read here and which I’ve linked to in my blog’s footer. (I’ll need to revise that policy pretty radically, as you shall see, but it’s probably a good thing to have anyway.) The harder task was creating that cookie banner, since it’s not just a static digital placard but an actual functional utility that captures a user’s cookie preferences and turns them into policies that impact the behavior of GA4. That is no small feat, and probably nothing I’d tackle on my own.
Before I pressed on I had a long, rambling discussion with
ChatGPT about how to get everything going. I learned a ton, including info
about the following:
- The various metrics I’d be able to get from GA4 (i.e., is this truly worth it?)
- What free utilities exist that could be leveraged for setting up the cookie banner and how to choose the best one
- Approximately how long it would take to set up the banner based on the chosen utility
- How to create a Google Tag and write an HTML script for my blog’s template that would invoke it
- How to create the HTML script that would invoke the banner
- How to pause GA4 if I have trouble invoking the banner (spoiler: I did)
- How to back up my blog’s HTML template before messing with it (though GPT didn’t suggest this, which again illustrates the difference between a) being able to describe how to do something, and b) taking the initiative to do that thing)
- How to debug my script and figure out why it’s not working
These weren’t just general instructions it provided that I’d have to suss out on my own. GPT4-turbo provided sample script text that actually worked (eventually). Here’s an example of its suggested script:
<!-- Your other
head tags -->
<script async
src="https://www.googletagmanager.com/gtag/js?id=YOUR_TRACKING_ID"></script>
<script>
window.dataLayer = window.dataLayer || [];
function
gtag(){dataLayer.push(arguments);}
gtag('js', new
Date());
gtag('config',
'YOUR_TRACKING_ID');
</script>
</head>
To reiterate, I am not a seasoned HTML jockey and would have struggled with this syntax, to say the least, were it not for the chatbot’s help. And even if I had originally built my blog from scratch (i.e., coding all the HTML myself without a Blogger template), I’d have been rusty enough now that I’d have been wise to leverage GPT for this task anyway. As I went through all this scripting, it dawned on me why a lot of people are worried about A.I. taking our jobs. This is just basic HTML but GPT was hugely helpful; If I were a full-on programmer and suddenly became (say) twice as efficient because I was grabbing blobs of basic code for simple operations instead of creating them from scratch every time, I’d naturally consider how all my colleagues have also become twice as efficient, and I’d start to worry about my employer realizing they could make do with half their programming staff. Scary stuff.
The upshot
Once GA4 was up and running, ChatGPT was very helpful in walking me through understanding all its metrics, not all of which were very intuitive. In a perfect world, I’d have discovered an average engagement time of ten minutes per post, indicating actual human readers. In reality, I learned that—guess what?—average engagement time is under three minutes, and GA4 shows way fewer page views than the Blogger stats. In other words, Blogger most likely is reporting on a lot of bogus visits from bots. If ChatGPT were like a really cool know-it-all big brother, it would have said, in response to my very first inquiry about the growth in traffic, “Dude, don’t trust the Blogger stats. They’re useless.” I wouldn’t have had to do all this research.
After asking ChatGPT a bunch of questions related to the delta in traffic as reported by each platform, I had it recalculate the ad revenue I might hope to get from my blog in light of the better data. It estimated about $0.40/month, and then went on to suggest a whole bunch of ways I could improve user engagement. I then led it on a thought exercise about how much of the real traffic is based on old posts, since a) albertnet posts are not timely, and b) the longer a post is up, the more views it will gradually accrue. GPT agreed with my assessment: that any improvements going forward would only marginally increase traffic and engagement, as they’d only apply to new posts.
Next I asked GPT for its best guess as to how much improvement I could achieve if I implemented all its suggestions … double? triple? tenfold? It replied that “doubling or tripling engagement is probably a reasonable and achievable short-term goal.” (This doesn’t impress me as intelligent … I think the chatbot is just highly suggestible.) I went on to ask, “Do you think it’s worth implementing these strategies with the goal of monetizing my blog through ad revenue?” It provided another long essay that concluded, “Yes, but with realistic expectations … treat ad revenue as a potential bonus or passive income stream, and consider other monetization strategies as well (affiliate marketing, sponsored content, or selling your own products/services).”
And this is where, I think, A.I. is still falling short. It’s great at helping the user with nuts-and-bolts technical tasks, especially those of the type performed countless times by other users (for example, inserting scripts to invoke GA4 and/or a cookie banner). But synthesizing a lot of information and drawing the best conclusion is still beyond its ability. By its own reckoning, my real, human traffic would bring in $0.40/month, and by implementing all its suggestions I might triple user engagement … but it failed to grasp that earning a mere $1.20/month isn’t worth any amount of effort. A.I. was ultimately unable to suggest the right strategy for me to take regarding my blog.
One last thing…
The sad part of this tale of exploration is how useless all my effort has ended up being. If I had any reason to suspect that, after fifteen years, my blog would suddenly go viral, I could keep an eye on Google Analytics to savor my success … but I don’t. I might as well be a frog looking in the mirror every morning to see if I’ve miraculously become a prince. Not that I actually care, mind you … as described here, I’m happy to be a humble frog croaking out my unsung song. But there’s no point bothering new readers with that cookie banner, especially since—as I recently discovered—the damn thing doesn’t even work.
This is another thing ChatGPT overlooked … it failed to suggest that I actually put that banner through its paces, which I’ve now done. Through basic experimentation I’ve discovered that it doesn’t end up mattering what preferences the user selects … his session is duly recorded in GA4. (Only if a user uses a Private or Incognito window are his sessions ignored … even if he allows all cookies.) Meanwhile, site visits from mobile users are not counted at all by GA4, I have just determined. That may be because I never got the banner to work on mobile, and Google can tell this and wants to observe the GDPR rules.
So now I have to go shut the whole thing down, to maintain GDPR compliance. The entire exercise was (to borrow from Shakespeare) “the expense of spirit in a waste of shame.” (Shakespeare was writing about lust, but I think his sonnet also covers the lust for money quite nicely.)
Check back in a week or so and (with ChatGPT’s help) I’ll have backed out the GA4 scripting and gone back to an unstudied, non-monetized blog with no banner. My privacy and cookie policy will have had a makeover as well. I’m no richer for this little exercise, but a bit wiser, and now you are too.
Other albertnet posts on A.I.
- I, Chatbot
- Almost Intelligent – Part I
- Almost Intelligent – Part II
- Smartphones & Artificial Stupidity
- A.I. Smackdown – Moto vs. Cortana vs. Siri
- Could Artificial Intelligence Replace Writers? – Part 1
- Could Artificial Intelligence Replace Writers? – Part 2
- Could Artificial Intelligence Replace Writers? – Part 3
- A.I. Smackdown – English Major vs. ChatGPT – Part 1
- A.I. Smackdown – English Major vs. ChatGPT – Part 2
- Schooling ChatGPT
- Will A.I. Steal Our Jobs?
- Tech Check-In - How Good is the Latest A.I.? - Part I
- Tech Check-In - How Good is the Latest A.I.? - Part II
Email me here. For a complete index of albertnet posts, click here.
