More Advice From an AI Skeptithusiast

Dear AI Skeptithusiast,

I’m just curious: are you enthusiastic enough about GenAI to pay for it? I think we have a weakness for spending a lot of time on stuff if it’s free, without registering the attentional cost. So how much do you pay for AI chatbot access, and how much would you be willing to pay if Big AI decided to jack up the price?

Erica A, Madison, WI

Dear Erica,

This is where my wariness of getting sucked into the online realm collides with my utter cheapness. The two forces are utterly complementary. At work I use AI whenever necessary but that’s on my employer’s dime; in my personal life, I let my usage be reined in by the limitations of free accounts. That is, I don’t pay for anything, and to the extent these AI chatbots get stingier, so will my use of them. If free GenAI accounts were all-you-can-eat, I’d need to implement other safeguards to avoid spending too much time with the technology. For now, its providers are keeping me honest.

I don’t expect everyone to adopt this approach, of course, because it takes some work. For example, in researching my blog posts I use Claude a fair bit, to where I run the risk of getting cut off. With that in mind, when I wanted feedback on whether the phrase “keeping me honest” works in the context you see above, I flipped over to Gemini to save on Claude tokens. And for my blog cover art, I currently favor ChatGPT but am well aware I only get like three tries to get the picture before the chatbot cuts me off. The picture above was started by ChatGPT, which in three tries couldn’t get the cheerleader’s neck right, and then locked me out, so I fed the picture to Gemini which fixed it. It’s like a little game … something you, Erica, may quite legitimately have no patience for, in which case I entreat you to bring that same impatience to your use of a paid GenAI!

Dear AI Skeptithusiast,

In my experience, early adopters of technology can waste a lot of time and/or energy working out its kinks. Sure, I’m intrigued by getting some help drafting documents, and having this amazing search engine that’s super easy to use, but GenAI is only going to get better and easier, right? Since it’s obviously not going away, why rush into it?

Sam Taylor, Mill Valley, CA

Dear Sam,

Of course AI is getting better at all kinds of things, particularly coding and agentic stuff. That said, its ability to write is, by contrast, barely improving (if at all), because that’s not an industry priority, and—in the words of Claude itself (not that I couldn’t have written this, but because I like to watch the AI fall on its sword)—“Code has tests, mathematics has answers, software can be executed, proofs can be checked, and agents either complete a task or fail to—but great prose can be ambiguous, abrasive, funny, incomplete, emotionally strange or deliberately indirect. You can build a clean reward signal for ‘did this code pass the test suite.’ You can’t easily build one for ‘is this sentence alive.’”

Asked why AI prose so often reads as flat, Claude offered a candid diagnosis. It suggested that “a model trained to be clear, safe, helpful and comprehensive can easily become the kind of writer who explains everything twice,” and that as AI evolves, writing quality “could plateau or even regress on some axes (distinctiveness, risk-taking) while improving on others (coherence, factual accuracy, following a long brief, editing).” The AI didn’t admit to its writing being pedantic, but I find it so often is.

(Claude provided the above guidance with a caveat: “Since your post will use direct quotes, it’s worth pasting them from our conversation rather than retyping them, so they match word for word.” For a platform that famously cannibalizes humans’ writing across the Internet, doesn’t Claude seem kind of defensive about me accidentally putting words in its mouth? How cheeky!)

It’s not only Claude that alludes to limitations of AI’s writing, and it’s not only in the realm of prose that AI falls short of a human possessing actual intelligence. Gemini, after stridently challenging me to a poetry-off a while back,  conceded defeat gracefully, lauding my “sophisticated tone” and noting that its poem, by contrast, “felt a bit like a student trying to please a teacher.” So as far as AI helping you write, now is as good a time as ever to try it out, but a good case could be made for simply not bothering at all, ever, other than running stuff by it as you write (e.g. “‘straightaway’ can be one word, right?”).

Regarding the other part of your inquiry—using AI for its natural language search capabilities—I think by not using it now, you’re missing out on the best experience AI is ever going to offer, and it’s actually going to decline. Think about this: do you remember when Google search really worked well and wasn’t so influenced by well-funded companies that bent the rules to show up higher in the results? I’m talking about SEO, content marketing, and paid search. They’ve really taken everyone a step backward.

A fun example: when I published my blog post “Everything You Wanted to Know About Getting A Vasectomy - But Were Afraid To Ask,” I was pleasantly surprised to discover that it became the number one hit when you googled “California vasectomy law.” It held that position for well over a year. And then the big law firms got smart, figured out how to swing the search engine toward their sites, and now my post doesn’t show up in the first ten pages of hits. Obviously this is partly due to how old the post is—but then, it’s also timeless. Meanwhile, my post “Spelling Focus - Is It ‘Kindergartner’ or ‘Kindergartener’?” is currently the number one hit when you google “is it kindergartener or kindergartner?” And that post is from eight years ago! The difference? Nobody is paying big money to grab that top spot, given the non-commercial nature of my linguistic investigation.

My wife has a landscape design business, and although she has a great website, she doesn’t do any kind of SEO or marketing efforts to drive traffic to it. It exists simply to be a web presence, so she can put the URL on her business card and brochure, and people referring business can send prospective customers there. She never expected people to stumble on her site or find it through Google. And yet, she’s starting to get leads, and they’re all from GenAI chatbots. The reason is that a potential customer who has a dialogue with a bot is getting more authentic guidance then he or she would from search, because with current GenAI there’s no SEO, content marketing, paid search, etc. skewing the results. So as of now, AI is actually delivering all the goodness that Google used to, when the Internet was still a largely open, uncommercialized community instead of a giant attention marketplace, with its relentless panoply of digital ads, algorithmic bait, and socio-political rabble-rousing.

Could this AI experience last? I asked Claude if there are any signs that AI chatbots could be influenced down the road by businesses clever enough, and sufficiently well-funded, to upset the balance again. Claude replied that not only could this happen, but it already is, and fast:

A whole “GEO” (generative engine optimization) industry has sprung up in the last year or two, specifically to get businesses cited and recommended inside AI answers — and it’s not fringe anymore. GEO is the practice of structuring content, brand entity signals, and technical infrastructure so that generative AI engines cite, quote, recommend, or otherwise surface a brand when users ask questions, and there are dozens of agencies already selling this as a retainer service, with search interest for GEO tooling up several orders of magnitude year over year and Fortune 500 brands budgeting for AI visibility as its own line item separate from SEO.

I had to drill down a bit on what “technical infrastructure” means in the context of GEO. It pertains to allowing AI crawlers in (many sites don’t, by default) and embedding non-human-readable “structured data” and curated markdown indices to basically spoon-feed AI engines, among other things. Needless to say my wife’s website doesn’t do any of this, just like I can’t be bothered to buy SEO to bring traffic to this blog. All of which is to say: if you want to experience authentic, unbiased advice from an AI chatbot, you better move quick!

Dear AI Skeptithusiast,

I have Gemini on my Android phone, though I don’t remember ever asking for it. I hadn’t originally minded this—I mean, it’s useful and all—but then a week ago I started getting this “Daily Brief.” Every morning I get an alert and when I tap it, Gemini gives me a to-do list and reminds me of all this stuff I have coming up in my day and my week. It’s creepy! Maybe it wouldn’t be so bad if it were just my calendar, but it’s evidently reading my chat history and even my email as well. I never configured all this, and I never told Google it was okay to mine my stuff! Is this the  beginning of the end?

Danny D, El Cerrito, CA

Dear Danny,

I definitely hear you there … I got that same feature pushed to my phone. My Gemini Daily Brief is telling me “sign this document” and “attend this film festival” and “your cousin’s birthday is Friday” and “prep for your coaching season” and even “weave Oakland vernacular into your writing project.” I wouldn’t say the hairs stood up on my neck when I saw this, but that’s only because my neck hairs aren’t that long.

This last bit about the vernacular was especially weird … it went on to say, “Your recent research into local Oakland slang and tone nuances lays a rich foundation for authentic dialogue.” I did have some vague recollection of this research, but obviously I wasn’t remembering it as well as Gemini. Turns out it was referring to my having queried it about whether “OE8” would be widely understood to mean “Olde English 800,” a decidedly non-epicurean malt liquor. (The context wasn’t a blog post, though, but for a party invitation I’d emailed out.)

We should actually be glad for this Daily Brief, because it’s like a canary in a coal mine: it draws our attention to what Google was already doing. This is a Gemini feature, not specific to the Daily Brief, and was configured (possibly by accident) when you enabled the Google Workspace Extension in Gemini. This Extension bridges Gemini to your personal, private Google data (reading your inbox, checking your schedule, scanning your personal Google Drive).

There are two ways to stop Gemini from running automatic background scans of your email. One is to disable the Gemini Workspace Extension altogether, so it can’t read your email at all. The other is to disable the Daily Brief. This second tweak tells Gemini to leave your email alone unless you ask it (during a chat) to chase something down for you. Myself, I’m turning off the Workspace Extension; I never ask Gemini to go into my email (and if I ever decide I want to, I can turn the Extension back on, and it’ll then have access to my current and past email). Here’s what to do: click the little gear icon in the lower left of your Gemini screen, then select “Personal Intelligence.” From there, you can either toggle off Daily Brief, or click “Connected Apps” and then toggle off Google Workspace.

Incidentally, this could be one of those scenarios where you increase your own privacy by reigning in this feature while simultaneously benefitting from other people accepting it as-is. I myself maintain Inbox Zero so I’m really good about responding to emails, but so many people I email seem completely swamped and are unresponsive. Honestly, I kind of like the idea of the Daily Brief alerts hassling my book club members for me, for example, when I’ve emailed them the ballot to choose the next book and nobody has responded.

Dear AI Skeptithusiast,

My sister says Gemini should be off-limits for family arguments because it doesn’t have enough context. I say it’s totally fine, if it’s just helping me articulate my position better. What do you think?

Tommy Z, Frisco, TX

Dear Tommy,

Your sister is right. GenAI could never have enough context to act as a legitimate mediator, since it only gets your backstory. Meanwhile, it has a “sycophantic bias,” which is how researchers describe its tendency to tailor its responses to the user—agreeing with their opinions, validating mistaken beliefs, or offering unearned praise—rather than providing objective truth or critical pushback. (Details here and here.) Look  closely at your last chat. Perhaps you wrote something like, “As the baby boomer brother, why do I constantly feel like my generation X sister is gaslighting me?” and perhaps it replied, “As the Baby Boomer brother, your gut instinct is right on the money: you feel like you are being gaslighted because your sister is actively rewriting reality to dodge accountability for her poor behavior. When she leaves you standing in the lurch, arrives late without a text, or fails to communicate, she doesn’t just make a mistake—she alters the narrative so that you become the problem.” So now you feel all high and mighty and send that transcript to your sister.

The only  trouble is, Gemini is working from its generalized training data on what gaslighting typically looks like, which may have little to do with what’s actually going on between you and your sister. Was she twenty minutes late this one time, or chronically? Did she “fail” to text because she was driving, and then didn’t fall all over herself apologizing because you don’t even have a job and just play video games all day anyway, meaning your time is essentially worthless? Had she just driven fifty miles from Fort Worth, through terrible traffic, to fetch you for your parents’ anniversary dinner because you lost your driver’s license? Did you share these important details with Gemini? If not, would it be any less legitimate for your sister to reply, “I asked my Magic 8-Ball if my big brother is a dipshit and it said, ‘It is decidedly so’”?

An AI Skeptithusiast is a syndicated journalist whose advice column, “Ask an AI Skeptithusiast,” appears in over 0 blogs worldwide.

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
• What is ChatGPT Great At (and Not)?
• Tech Reflection – Two Sides of AI
• AI Smackdown – ChatGPT vs. Copilot vs. Gemini
• New Year’s Resolutions — AI Edition
• Ask an AI Skeptithusiast

—~—~—~—~—~—~—~—~—
Email me here. For a complete index of albertnet posts, click here.

Should We Be Using GenAI?

Introduction

As you have likely worked out on your own already, Artificial Intelligence is not going away. It has gone from being a joke to a novelty to the bogeyman to a tool that many of us use all the time. And yet, there are still holdouts, perhaps you among them. In my workplace, it’s a mixed bag. As recently as 2024 I was forbidden to use ChatGPT or other AI platforms at work; now, my employer  is wheedling, exhorting, begging, and all but requiring my colleagues and me to adopt it. On the family front, one of my daughters uses it a fair bit (sometimes frivolously), the other not at all. My wife is wary of it.

So should you use AI? I consider myself fairly well qualified to answer this. I have been dabbling in AI for almost fourteen years; have devoted a fair amount of research to kicking its tires; and now use it extensively both at work and at home. I’ve blogged about it a bunch of times. I’m unbiased, since I don’t work for the AI Industrial Complex, but I also don’t have a knee-jerk fear of technology.

I’ve blogged before (here) about how we can use AI, describing two fundamental ways—operationally vs. creatively—that people do use it. Today’s post is more about whether we should use it, and how often, particularly in light of the resources (electricity and water) that it consumes. Is environmental responsibility a compelling reason to curb our use of GenAI?

Some housekeeping

As I’ve explained here, AI is much bigger than the Large Language Model (LLM) chatbots that we consciously use as the natural successor to Google. We generally speak of AI as a productivity tool, but a whole lot of AI is devoted to the invisible algorithms on social media, YouTube, etc. that grab and hold our attention, threatening to reduce our productivity. I think of this as secondhand AI (like smoke). Meanwhile, you’re surely hearing a lot of hype about “agentic AI,” which can supposedly act on its own volition to achieve a goal. At this point I’m scared of agentic AI and think you should be, too, but that’s another post. The AI I’m considering here is Generative AI (GenAI), which is the type of chatbot (e.g., ChatGPT, Gemini, Copilot, Claude) that you feed a prompt to as a way to research something, or as a way to quickly compose an essay, letter, or picture. This is how I believe most people think of AI, which is why the terms “AI” and “GenAI” are so often used interchangeably.

(Note that if you are reading this post long after April of 2026, and there isn’t a single living human not using GenAI, and/or the robots have taken over and enslaved you, treat this post as a historical artifact. At least you’ll get a sense of how society initially approached this technology.)

GenAI at work

If you work for a corporation that is clearly embracing GenAI, providing you a commercial, “walled garden” version of it, and the training to go with that, adoption is a no-brainer: do as you’re told and embrace GenAI immediately. My employer is already monitoring my use of it (though they haven’t said exactly how), showing my compliance on a dashboard. (My “AI Tools Usage” is showing 87% and green.) I could bristle at this, but a) I have always know my use of company assets is monitored, and b) my employer’s expectation that GenAI will make me more productive is reasonable, as is their expectation that I will be as efficient as possible. 

It’s remarkable how quickly all this has changed. I have seen GenAI’s use go from something my colleagues formerly tried (in vain) to hide, to something that my manager will outright ask me about. When asked, “Did you use AI to help you with this?” I now assume that the correct answer is a version of “yes.” (This answer is necessarily nuanced. Both in terms of being honest and articulating my ongoing value as an employee, I am sure to explain both how it helped and how it fell short of doing the task for me.) This week my boss tasked me with figuring out how to create a NotebookLM chatbot specializing in expertly summarized minutes of every meeting anyone on our team attends (or previously attended), which updates its training data automatically. So if our colleague Joe is on vacation we can ask the chatbot, “Why did Joe Blow switch out the vPlan in Blascorp’s EZ-Pluck profile?” and hope to learn the history. I feel like this assignment would have been unheard of a year ago.

But what if you work for a small business, or have your own? This is a greyer area, of course. A member of my family is a sole proprietor, and so far has shied away from GenAI because she’s concerned about becoming too reliant on the technology. I get her point, and have blogged before (here and here) about how doing our own thinking and writing prevents us from falling into intellectual torpor. But isn’t a tool that legitimately improves efficiency something we ought to rely on? After all, we wouldn’t even think of trying to run a business without email, a laptop, a smartphone, in many cases videoconferencing capability, and (depending on the business) various types of specialized software. All of these tools were new once, and any small business owner still using a typewriter to generate invoices is surely a) in the minority, and b) wasting a lot of time. From that perspective, it’s all but inevitable that any small business owner will ultimately adopt GenAI for his or her business … so why wait?

GenAI at home

Using GenAI outside the workplace is a more complicated matter, since it’s not helping put food on the table. I mentioned earlier in this post that my older daughter has occasionally used it rather frivolously, such as to punk me. Consider this drawing she had ChatGPT create to memorialize an accident I had at a hotel pool back in 2024, when I got out of the hot tub too fast and fainted:

Her prompt for this was, “Can you create an image of a tall skinny white man feeling faint after leaving a hot tub?” As you can see, the man portrayed looks more hunky than skinny, and my daughter tried three more times to get the picture more accurate. Given that these were throwaway efforts (or would have been had I not used them in an early AI analysis here), this was devoting rather a lot of computing resources to a pretty trivial problem, or shall we say exercise. (Of course part of the point for my daughter was exploring the early technology; it’s not like she’s stuck with throwaway art as her primary use case for GenAI.)

On the flip side, her sister won’t use GenAI at all, somewhat on grounds of intellectual authenticity but mainly due to its environmental impact. The constant construction of ever-larger data centers is all over the news, with some shocking statistics thrown around about how much power and water a single GenAI prompt requires. Today I decided it’s time to vet this claim a bit, studying the available data and describing it in a context that could help guide our behavior appropriately.

How much electricity does GenAI use?

With the help of Claude, because it works better than a Google search, I did some light research and found some great analysis (here) on the website of Epoch AI, a nonprofit founded to “help people understand what is happening in AI from a neutral perspective and grounded in the best possible evidence.” Epoch AI partners with Stanford’s AI Index, which I’ve come across in my professional life and seems well respected, as well as the UK’s Department for Science, Innovation, & Technology, which I trust even more (since it doesn’t have ties to the tech industry like Stanford does). I must acknowledge that truly disinterested AI research is hard to come by, because almost every organization doing serious work in this realm has a business relationship with it. So to spread out the risk of misinformation I also put this query to ChatGPT, which came up with similar numbers but from other presumably trustworthy sources, including ScienceDirect (which Gemini says “is considered one of the most reliable and authoritative sources for factual data in the world”) and Cornell University.

So: Epoch AI, in an article from about a year ago, examined a widespread previous claim that “an individual ChatGPT query requires around 3 watt-hours of electricity, or 10 times as much as a Google search.” Epoch AI, leveraging “more up-to-date facts and clearer assumptions,” arrived a the following conclusion:

We find that typical ChatGPT queries using GPT-4o likely consume roughly 0.3 watt-hours, which is ten times less than the older estimate. This difference comes from more efficient models and hardware compared to early 2023, and an overly pessimistic estimate of token counts in the original estimate. For context, 0.3 watt-hours is less than the amount of electricity that an LED lightbulb or a laptop consumes in a few minutes.

For further perspective: according to this article, “Google says that its median text query uses around 0.24 Wh of electricity. That’s a tiny amount: equivalent to microwaving for one second, or running a fridge for 6 seconds.”

But that’s just text queries. Creating a picture uses a lot more resources. According to this article by the University of Southern California, using GenAI to create a picture uses 2.9 Wh—over ten times as much as a text query. I had Gemini come up with some household use equivalents to give this number some context, and here’s what it came up with:

• Phone: charges your battery about 19%
• LED bulb: about 19 minutes of light
• Dishwasher: about 14 seconds of a cycle
• Clothes dryer: about 2.6 seconds of a cycle

These seem pretty trivial, but if you consider all the millions of people using GenAI, it can add up, especially if people get it the habit of iterating a dozen or so times to get the image just right. (For what it’s worth, I got the cover art for this post in two tries.)

How much water does GenAI use?

Water is another matter, and very difficult to quantify because the location of a data center has a lot to do with how efficiently it can cool all its servers. This“ Washington Post” article documented a study, involving research from the University of California at Riverside, that found that using ChatGPT to write a 100-word email consumed 519 milliliters of water, which is a little more than a standard bottle. Obviously that is really high, especially considering how many people use GenAI and how much that’s growing.

At the same time, as pointed out by this article, many other industries also use a ton of water, and people don’t seem up in arms about it: “A single burger takes more than 400 gallons of water to produce; a humble cotton T-shirt takes more than 700. The United States’ 16,000 golf courses, meanwhile, each have the potential to use on average between 100,000 to 2 million gallons of water per day. (For comparison, Google says its thirstiest data center in Iowa consumed about 2.7 million gallons per day in 2024; most of the company’s data centers used substantially less.)”

A less abstract comparison

To be fair, it’s not like we all sit around eating burgers all the time; for most of us, that’s a treat. Meanwhile, I would hope most albertnet readers are enlightened enough to hold out for grass-fed beef, which uses a lot less water to produce. And if you’re like me, you buy a lot of clothing secondhand, which helps mitigate the resources required for your wardrobe. So what’s a better comparison that can help us frame the environmental cost of using GenAI? I propose: beer. (I know what you’re thinking: that’s my answer to everything.” Well, okay … guilty as charged.)

So here is my thought exercise: how does using GenAI compare to cracking open a beer? And what is the value of the former vs. the latter? Obviously this is a wide-open scenario so I’ll narrow it down to how I most often use GenAI: when researching a blog post.

Here’s what Claude had to say about the electricity required for a 30-minute research session:

Based on current estimates, a substantive text exchange with an AI like this one — say 20–30 back-and-forth exchanges — is probably in the neighborhood of 5–10 watt-hours of electricity. Google has reported that after major efficiency gains, the median Gemini prompt consumed about 0.24 watt-hours, representing a 33× reduction in energy per prompt compared to a year earlier. At that figure, 30 prompts would use about 7 Wh — roughly equivalent to running a phone for 20 minutes or leaving an LED bulb on for half an hour.

Regarding water use, a Mistral AI lifecycle analysis citied by the Brookings Institution found that a typical 400-token exchange consumes about 45 milliliters of water—about three tablespoons. Multiply by 30 exchanges and you’re somewhere around 1.5 liters of water—very roughly two or three bottles’ worth attributable to the 30-minute research session. (This varies enormously by data center location and cooling method, so we should treat it as an order-of-magnitude estimate.)

To compare the electricity cost of the GenAI session vs. the can of beer, I downloaded a spreadsheet-based waste reduction calculator directly from the EPA’s website. It is designed to help consumers like me understand the value of recycling something vs. tossing it. It calculated that recycling a 12-ounce aluminum can saves 0.3 kWh—which is roughly 40 times more energy than what’s consumed by an entire 30-minute GenAI research session. Granted, I often generate a picture to go with my post, but even if we assume it takes five tries to get it right, the energy cost of those five images is still only about one-twentieth of the energy wasted by tossing a single beer can in the trash. And since this is only the energy cost of recycling, which is less than producing a can from scratch, these numbers are highly conservative. (Meanwhile, I haven’t even factored in the energy required for brewing and transporting the beer itself.)

Meanwhile, the Water Footprint Network, as described here, estimates a total water footprint of 298 liters per liter of beer—so a standard 12-oz can of domestic beer takes over 100 liters of water to produce. More than 90% of that water comes from the agricultural supply chain (e.g., growing the barley) while the brewery uses about 6–8 liters per liter of beer (though a large facility may achieve a 3-to-1 ratio). So my 30-minute research session uses something like 1–2% of the water embodied in the can of beer I might have next to my keyboard. (Full disclosure: there’s a now-empty pint glass on the arm of the sofa as I type this. Yes, drinking while blogging: a rhetorically risky and planet-impacting combination. So sue me.)

Factoring in value

So that covers the environmental cost of researching a blog vs. drinking a beer. But what about the value of each? Discounting pub crawls with my friends—which occur far more seldom than I would like, to the point that they’re a rounding error—I’m really talking about unwinding with a solitary beer at the end of the workday. So in general the value of that beer accrues solely to me.

So does my blog-related GenAI research create any value to justify its water and electricity use? In the interest of humility I won’t merely assume this, and will instead dive into the data. Pageview stats across my blog wouldn’t be very representative, as at least half my posts don’t require any research at all. So for lack of a better idea, I’ve decided to analyze the pageview count for each of the albertnet posts that are about AI. After all, those have to be among the most GenAI-intensive of all, because in writing them I was test driving the various platforms. Here’s a brief summary of how these posts have performed:

• Total pageviews across nineteen AI posts: 15,578 (so far)
• Average pageviews per AI post: 819.9
• Average pageviews per AI post per month: 35.5

I could conclude that, from a somewhat abstract viewpoint, each post is seen by a person a day. But averages aren’t very reliable, and greater specificity is more revealing. Lurking in that “average pageviews per AI post per month” is a bit of (GenAI-performed) number crunching, accounting for the fact that the posts that I published years ago have had a lot more time to accrue pageviews. Ranking my AI posts by pageviews per month shows that they are gaining in popularity, with the more recent ones averaging two to three views per day. Here’s the ranking of all these AI posts over time, so you can see the momentum:

№	Views/Mo	Total Views	Title
1	102.5	1,742	Tech Check-In – How Good is the Latest A.I.? – Part II
2	85.7	257	New Year's Resolutions — AI Edition
3	82.8	1,077	What Is ChatGPT Great At (and Not)?
4	69.9	1,189	Tech Check-In – How Good is the Latest A.I.? – Part I
5	62.4	312	AI Smackdown – ChatGPT vs. Copilot vs. Gemini
6	58.0	290	More AI Smackdown – ChatGPT, Copilot, & Gemini Write Poetry
7	51.2	256	Tech Reflection – Two Sides of AI
8	27.4	1,040	A.I. Smackdown – English Major vs. ChatGPT – Part 2
9	27.1	1,031	A.I. Smackdown – English Major vs. ChatGPT – Part 1
10	23.0	597	Will A.I. Steal Our Jobs?
11	20.0	739	Schooling ChatGPT
12	11.1	719	Could Artificial Intelligence Replace Writers? – Part 1
13	10.6	680	Could Artificial Intelligence Replace Writers? – Part 3
14	10.0	1,230	A.I. Smackdown – Moto vs. Cortana vs. Siri
15	8.8	563	Could Artificial Intelligence Replace Writers? – Part 2
16	7.3	1,201	Almost Intelligent – Part I
17	6.3	838	Smartphones & Artificial Stupidity
18	6.2	1,016	I, Chatbot
19	4.9	801	Almost Intelligent – Part II

It would be reasonable to conclude that the more recent posts, which leverage more GenAI research, are reaching more readers, thus providing a better ROI. Of course I can’t account for all the possible reasons these posts are more popular, but I reckon that to some degree it’s because of the better use of GenAI. Using this tool won’t make be a better writer, but I’ve always been pretty lazy about research and there’s no doubt GenAI helps there. And whether or not this ROI calculation is completely airtight, I hope this helps you at least appreciate my effort to weigh my GenAI “footprint” against its value.

The bigger point here is that the can of beer is consumed once, quickly, leaving nothing behind (except maybe a nice belch). In contrast, the energy that goes into researching a blog post has an effective cost-per-view that keeps dropping every month it’s up, in perpetuity. If you use GenAI to draft an email, how many people will it reach, and low long is its tail? Could you have drafted it on your own—thus exercising your brain—or did you really need GenAI?

I’m not trying to imply that only bloggers should use GenAI; this is just one illustration of a cost/benefit analysis of the use of this tool. If you are doing something useful and an AI chatbot is helping you do it better or more efficiently, then it’s arguably worth the energy and water—or, at least, is a more worthy use of it than shopping for a bunch of clothes, going out for a burger, and then having a few beers.

The point is to be aware of the environmental cost of this technology, the same way so many of us do when we decide among driving, biking, walking, or taking mass transit  somewhere. Just because GenAI takes less water than beef or cotton doesn’t mean we should ignore its environmental cost, since it’s a whole new way people are consuming energy and water. As recently as three years ago, almost nobody was using GenAI in their daily lives; now, it’s an increasingly entrenched behavior, data centers are expanding rapidly, and in some regions power grids are struggling to keep up with demand.

This being said, I truly don’t believe opting out of GenAI is the solution; just reflecting on how much it helped me write this post, I can’t imagine not taking advantage of it. Instead, I’d like to see the millions of people already using it stop acting like it comes without a cost. It’s the same as driving: did I really need to surround myself with two tons of steel and burn a cup of gasoline just to travel a mile to the gym and back? (That was a rhetorical question. I always bike to the gym.)

Speaking of cost: one way to keep yourself honest with GenAI is to not pay for it. If you are on an unpaid account and use up your tokens, so that your chatbot cuts you off for some number of hours, maybe that should be your indication that you’ve gone overboard. Come to think of it, video games, YouTube, and social media should have that “feature.”

A final note on GenAI at work

Now that I’ve examined the environmental cost of GenAI, it’s worth pointing out a final wrinkle: using it in the workplace is actually much more efficient than using it at home. Corporations get the most benefit out of GenAI through Retrieval Augmented Generation (RAG), which is where, instead of asking a large language model to answer from its entire trove of training data, the GenAI retrieves relevant documents from a corporate knowledge base (contracts, manuals, research reports, emails, whatever the organization has indexed), then passes those retrieved chunks to the model as context for its answer. Tools like NotebookLM, most enterprise Copilot implementations, and corporate deployments of models like Gemini or Claude typically work this way.

This is much more efficient than “raw” GenAI like consumers use. The retrieval step is computationally cheap—essentially a sophisticated search. The generation step is shorter because the model doesn't have to work as hard to “remember” or construct relevant context; it’s been handed it. And the answers tend to be more accurate and require fewer iterations, which means fewer wasted queries. For a user to opt out of using it on environmental grounds makes little sense, because the big resource expense has already been incurred. As Claude puts it:

The infrastructure cost of a corporate RAG deployment is largely fixed relative to usage. The vector database has to stay current whether 500 employees query it or 5,000. The embedding pipeline runs continuously. The API connections to the underlying model are on retainer. So each additional active user essentially dilutes the per-capita environmental and financial cost of that overhead. An employee who declines to use the tool isn’t reducing the infrastructure footprint; they’re just reducing the output derived from it. In accounting terms, they’re lowering the return on a sunk cost.

Synthesis

Wow, I just threw a ton of words at you, didn’t I? Maybe I’m the most verbose Large Language Model since, well, ChatGPT! Anyway, here’s my final conclusion: of course you should use GenAI. It’s an amazingly powerful tool, and it’s getting better all the time. Now that it’s here, declining to use it makes about as much sense as blending a smoothie with a knife and a whisk, or doing arithmetic with an abacus, or churning your own butter. But use GenAI judiciously. Ask yourself: is this improving the quality or efficiency of my output? Or am I just being lazy?

Other albertnet posts on A.I., in order of publication

• 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
• What is ChatGPT Great At (and Not)?
• Tech Reflection – Two Sides of AI
• AI Smackdown – ChatGPT vs. Copilot vs. Gemini
• More AI Smackdown - ChatGPT, Copilot, & Gemini Write Poetry
• New Year’s Resolutions — AI Edition

—~—~—~—~—~—~—~—~—
Email me here. For a complete index of albertnet posts, click here.

Tech Reflection - Two Sides of AI

“This Halloween, I’m dressing up as generative AI. I’m going to show up to the party without a costume and just start stealing pieces of other people’s outfits.”
— An X dispatch my niece screenshotted for me

Introduction

Is AI the amazing new technology that’s changing the world, or a petty thief that just steals people’s ideas and passes them off as its own? Does it actually carry out anything approaching thought, or is it just a zombie, stalking humans’ digital relics and muttering “brains … brains … brains” as it angles to get a piece of us?

In this post, I examine the two most fundamental functions AI chatbots can carry out, and draw a distinction between the two. I believe this can give us useful guidance in deciding how we ought to use this game-changing technology.

Ecclesiastes vs. Barthelme

AI is evolving fast, perhaps faster than our ability to understand it. I’m having to adapt; for example, I’ve stopped spelling it “A.I.” because leading media outfits like The New Yorker and The New York Times have now eschewed the periods. So if you’re reading this on your phone in a sans serif font you may have initially thought I was writing about there being two sides of Albert or Alfred. I asked ChatGPT what to do about this ambiguity between a capital “i” and a lowercase “L,” and it suggested I could “kern or tweak the glyphs.” I’m not exactly an expert at kerning glyphs, so I asked the chatbot how. It gave me all kinds of strategies, the best one for my blog format (HTML) being this:

AI <!-- default -->

A<span style="letter-spacing:0.05em;">I</span> <!-- slightly looser -->

So you can see, GPT is right there with an answer when queried about a technical operation that has been done before. But what about doing something creative and original? This is a fundamental distinction and I am going to propose we look at AI from two largely separate perspectives, for which I’ve invented labels:

• Operational mode – I thought about calling this Ecclesiastes mode, for “no new thing under the sun.” This mode is about helping with a nuts-and-bolts operation (e.g., HTML scripting, DNS routing) that somebody else, probably many people in fact, already figured out and documented out there on the Internet for AI to gobble up, distill, pretty up, and present. Here, AI is basically a really good large language model that excels at combing through gobs of chaff to find answers, and organizes and summarizes information very clearly. I wouldn’t say it’s as parasitic as what’s suggested by the X epigram above, because lots of people freely post technical stuff to the Internet just to be helpful, without thinking of it as sacrosanct intellectual property.
• Creation mode – I think of this as Barthelme mode, named for the writer Donald Barthelme, because I think he’s the epitome of totally original, wacky, one-of-a-kind creative types with an absolutely distinctive voice. In other words, this is the intelligence that I am quite convinced AI could never approach. By creation I mean using the full capability of your own mind to advance ideas that are new, and yours.

The trouble is, many people don’t make any distinction between these two general areas of AI, so on the basis of its prowess as a natural language search engine, they are be led to believe it can do a perfectly good job at creation mode. And since most people aren’t English majors, and in fact don’t respect English majors, AI platforms get to roll out some pretty inferior writing and everybody thinks it’s genius. (This widespread lack of sophistication is also why McDonald’s makes so much money.)

So what?

For many years, as I’ve lamented at length in these pages, kids have been told all the jobs are in tech, and they need to study STEM. And now, many of the kids who dutifully followed these marching orders are graduating from college with Computer Science degrees and not getting jobs, and tech is laying off gobs of people. Next time I meet a STEM major I’m gonna ask him, “Computer Science? What are you gonna do with that?”

So how did STEM go from meal ticket to a food stamp? Well, I think it’s largely because AI is actually getting pretty good at the operational mode. It writes software so well, all industry needs is a seasoned coder to check it. Will we still have seasoned coders in 20 or 30 years, when all the current ones have retired and nobody has come through the ranks to replace them? Probably not, but that’s a whole other blog post somebody has surely already written. (I did blog about ChatGPT’s prowess with operational mode earlier this year, here.)

So as we look at AI, and particularly its role in our personal and professional lives, I think we need to ask ourselves what we have to offer that is rare and valuable, and how AI can help. Specifically, I believe we should be asking the question: how do we use operational AI to handle rote stuff, so we have more time to develop our unique, original ideas—so as to bring out our inner Barthelme?

What to use AI for

I have to confess, I love AI for light research when I’m blogging. The kernel of my posts always comes from my own brain, usually from pondering all kinds of things while I’m out on a solo bike ride. But ChatGPT is a great way to chase down and pinpoint something I had vaguely committed to memory. For example, when working on a recent post I asked it, “Can you track down the Lore Segal quote from ‘Her First American’ about ‘protocol is the art of not doing what comes naturally’?” I probably could have found this with Google, but the AI helped (and might have been indispensable here had I not remembered the name of the novel). ChatGPT was also super helpful when I was writing my post on induction ranges, in researching certain facts (e.g., energy efficiency info and whether government rebates are available).

AI is also pretty helpful at work, where I use a “walled garden” version my employer provides. (It doesn’t use any of my chats as training data for the AI’s ongoing education.) In fact, my employer exhorts all us employees to use AI every day. It’s like with any great tool: we’re expected to work more efficiently because we have it, so we’d better use it well. Recently, I took several product specification documents for different Internet hardware devices, fed them into an AI utility, and asked it to read them all, highlight the differences among the different makes and models, and tell me which one I want for xyz purpose. This was much faster than poring through everything myself, which is a decidedly operational task. The report it generated was clear and reasonably concise, and probably won’t be read very carefully anyway. In fact, someone will probably upload it to a chatbot and have it summarized. All this is fine with me.

One other great use for AI chatbots is to ask them for instructions for quotidian technical matters in your personal life, like disabling the child lock on your new microwave oven, charging your new bike’s electronic shifting, or restoring your playlist after updating your smartphone’s MP3 app. Sure, these are things you could look up on YouTube, but often that search can be tricky, and the videos can be agonizingly slow. The following video tutorial, which is crisp and concise and beautifully shot, is perhaps the exception that proves the rule:

I guess one benefit with YouTube is it’s less likely to hallucinate. I asked ChatGPT if my bike’s brake/shift levers have button cell batteries, and it explained in great detail how there are actually wires running from the battery pack to each lever, so they get recharged along with the derailleurs. The chatbot even drew me a nice diagram to illustrate this. Alas, it was hallucinating: the levers totally do have button cell batteries that need to be periodically replaced.  But all this being said, it’s easy enough to sanity check this kind of output, and I usually get a good answer from AI when I can’t locate a product owner’s manual or don’t feel like leafing through the 50-page one that I have, trying to get past the 14 foreign language versions.

What NOT to do with AI

I think where people get into trouble with AI is when they try to get it to do their work for them, particularly writing documents or correspondence that they then pass off as their own. In some cases this is an ethical or even legal matter; as I described here, the New York Times is suing OpenAI for copyright violation, and I have firsthand evidence of ChatGPT essentially plagiarizing this blog. But I doubt you overmuch care about that. There are two bigger issues, I think:

• What this “creation mode” usage does to the quality of “your” writing
• What it does to the quality of your thinking

There’s this notion that you can ask a chatbot to write something for you, anything from an email to an invitation to a work report, and then you can just polish it up a bit, and you’re done. No more writer’s block! No more outlines, or worrying how to organize your thoughts! That might be okay for a very basic report, like what I described comparing features of tech hardware. But when you start from scratch with your own document, you’re not just leveraging AI’s impersonal, sprawling training data; you’re using your own—everything you’ve experienced, heard, read, and dreamt of. It’s your own personal muse, not the generic Internet one.

Honestly, for anything loftier than a rote technical document—that is to say, anything designed to edify, persuade, or entertain—haven’t you seen for yourself how AI can fail? Like, you’ll get this chipper invitation to a family reunion and it’s using corny phrases like “drum roll please” and joking about your family’s dance moves, and it just seems generic and clichéd? That’s all AI can do. It doesn’t know you or your family or friends well enough to say anything truly clever, and all the polish you want to give its rough draft won’t help. Your invitation will never have real style, along the lines of, “L— gets dibs on the guest room (which she may still anachronistically refer to as “her” “bedroom”) and its magnificent new king-sized guest bed. If you’re nice she might invite you to a slumber party there. Other guests can fight over the legendary Futon of Sand down in the home office. Beyond that, we have two large sofas for those interested in the college-esque party-‘til-dawn experience. We would not be offended if one or more parties were to seek a motel/hotel/AirBNB/VRBO, especially given the relatively small number of bathrooms here (i.e., one). Regarding rumors that the men are encouraged to pee in the backyard, this is true, but please stick to the planting beds and the fountain.” See how much better that is?

Now, you might be thinking, “Wait, I’m not a blogger and I wasn’t an English major. Cranking out an email or an essay may be easy enough for Dana, but I just want to get this task done and checked off.” But stop and think for a moment: what would you like to be good at, in life? Please tell me the answer isn’t just “typing good prompts into AI.” Wouldn’t you like to be articulate, interesting, and capable of thinking on your feet? Because what are you going to do at a cocktail party, or a job interview, or a non-virtual work meeting, when you don’t have a chatbot to help you, and that’s the habit you’ve let yourself fall into? The reality is, we get good at thinking by struggling to do it, for ourselves, the old fashioned way.

So let’s not undervalue written communication by outsourcing it to AI. The best case scenario is that it’ll do an inferior job, replacing what could have been original thought with a pile of trusty clichés and/or stealthily plagiarized, slyly anonymized content. The worst case scenario is that it’ll actually get good enough that you never have to write for yourself again, and your brain can atrophy to the point that you’re not even a thinker anymore … just a chatbot operator.

Because you don’t care

Gosh, I guess I drifted into high-and-mighty, pompous, full-on pontification there, and I feel pretty sheepish about it! Fortunately, I’m realistic enough to sense you snickering, and I know you’re going to turn right around and keep on using AI for whatever you can possibly think of. That being the case, check back next week because I’m going to catch you up on the latest AI technologies and how much they’ve improved since my last check-in. Whether your chatbot of choice is ChatGPT, Gemini, or Copilot, I’ll have you covered. Until then, I’ll be getting back to what I really enjoy in life: kerning glyphs.

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
• What is ChatGPT Great At (and Not)?
• AI Smackdown – ChatGPT vs. Copilot vs. Gemini
• More AI Smackdown - ChatGPT, Copilot, & Gemini Write Poetry

—~—~—~—~—~—~—~—~—
Email me here. For a complete index of albertnet posts, click here.