writing and blogging

Unlock beekeeping secrets with chatbots, but be wary of disinformation

It's okay to learn beekeeping from a chatbot, but be sure to verify anything that seems fishy. Deposit Photos

I worry about those who decide to learn beekeeping from a chatbot. Chatbots can provide some good information, but they also spout nonsense.

Inside: This article, published in March 2023, is already old news to many. Still, it contains some curious examples of beekeeping advice from a chatbot.

Everyone is turning to artificial intelligence these days. As a website owner, I receive dozens of emails per week extolling the virtues of AI. I’m told I can save time, money, and frustration by allowing AI to write blog posts for me. For a nominal price, my week’s articles — enhanced for search engines, grammar-checked, and guaranteed plagiarism free — can appear in seconds. No subject is too difficult, no science too obscure.

This article first appeared in American Bee Journal, Volume 163 No. 3, March 2023, pp 315-317.

I’ve been ignoring these sales pitches for months, thinking “yeah, right” as I scrub them from my inbox. But then on a dreary, drizzly December day, I fell for it. I was suffering from overload, behind in every aspect of life, and frustrated with blogging. Duly harassed, I said, “Okay, show me.”

In an instant, I signed up for a free account with ChatGPT (Chat Generative Pre-Trained Transformer) and started asking beekeeping questions. Before I could hit the question mark, the answers began typing themselves across my screen.

What is ChatGPT?

By now, you know that ChatGPT is a natural language processing model of artificial intelligence. It is “trained” to answer questions in a human, conversational way. It “learns” by reading the internet and responds by using language rules. In short, you ask a question and the chatbot gives you a written answer.

One of the first things I noticed was the quality of the writing. Overall, the chatbots know English. The wording is grammatically superior to most stuff I read online, and I found no irritating phrasal verbs (like cook up, plant up, fry up, or level up) that drive me to distraction. I found only small amounts of passive voice and no agreement errors. Pretty good for instant results. Amazing for a robot.

And some answers weren’t terrible. Consider my very first attempt at eliciting beekeeping information from a machine. It asked no follow-up questions and didn’t ask me to clarify or define my terms. Just like a genuine second-year beekeeper, it was utterly confident and self-assured. I asked, “In honey bees, what is drone eviction and why is it important?”

The chatbot replied, “In honey bee colonies, drones are male bees that mate with queens from other colonies. Drones do not have stingers and do not participate in the day-to-day tasks of the hive, such as gathering nectar and pollen or caring for the young.

“During the fall, as the days grow shorter and the availability of flowers decreases, the worker bees in the hive begin to prepare for winter. One of the ways they do this is by evicting the drones from the hive. This process is known as drone eviction.

“Drones are evicted because they are not able to contribute to the survival of the hive during the winter months. They do not help with gathering food or keeping the hive warm, and they consume valuable resources that could feed the young bees and the queen. Removing the drones from the hive allows the worker bees to focus on preparing for and surviving the winter.”

The chatbot seemed to know all about drone eviction. Rusty Burlew
The chatbot seems to have a decent comprehension of drone eviction. Rusty Burlew

Not (totally) bad for a robot

Now, remember, this answer was instantaneous. It suffers from wordiness and a bit of passive voice, but the grammar, sentence structure, and logic are remarkable. Even more impressive, the answer is basically correct.

As an editor, I would say the bit about stingers is off-point and should be deleted. Conversely, the answer should explain how workers evict drones and what happens to them afterward, tidbits that could add interest to the passage. Still, it’s not bad.

The things eggs eat

I continued to ask the chatbot dozens of beekeeping questions. Not all the answers were as helpful as the first one. According to the chatbot, CCD is still the major threat to honey bees, varroa mites continue to thrive by slurping hemolymph alone, and bees can transform refined sugar syrup into pure honey in just a few days.

When I asked the chatbot to explain the purpose of bee bread, it told me the bees feed the eggs a mixture of pollen and nectar, a diet that provides them with the nutrients they need to grow and develop into larvae. Do you see? The answers are close (and entertaining) but a tad iffy.

Who knew honey bees eggs could eat anything? Pixabay
Who knew honey bees eggs could eat anything? Pixabay

How to train a chatbot

After playing question and answer for a while, I decided to learn how AI writing works. The simplistic explanation goes like this: The bot “reads” information available on the net. Lots of it. ChatGPT claims to have already read a large portion of the internet and continues to read more. The “handlers” also trained it in the grammar and vocabulary of multiple languages.

According to the website, ChatGPT learns to write by calculating what words are most likely to follow other words. To me, that sounds like a questionable practice, but I’m digitally inept and know it. I can’t say how somebody else (or someboty else) learns.

Writing without understanding

But here’s the real-life catch: The chatbots don’t “understand” anything they utter. And since they don’t know the meaning of the sentences they string together, you can get contradictions, strained logic, or complete nonsense.

For example, when I asked the chatbot about fat bodies in winter bees vs. summer bees, it wrote [emphasis added], “Fat bodies in honey bees play an important role in the bees’ metabolism and energy balance. In winter bees, fat bodies are larger and more developed than in summer bees, as the bees need to use the energy stored in their fat bodies to survive the winter months when there is little or no food available.”

Then, about four paragraphs down, it added, “Winter bees have smaller fat bodies than summer bees, as they do not have access to as much food and need to rely on stored energy to survive.” So, according to the chatbot, fat bodies in winter are larger and smaller than fat bodies in summer.

I suppose that contradiction could be true if you were comparing the size of fat bodies of young winter bees with those that survived through the winter. But the chatbot never suggests that.

I can only conclude that if you are writing an article and you already know your subject, you could edit the paragraphs and end up with passable content. But if you don’t know your subject before you begin, and you let the chatbot write your article, you could look pretty foolish in short order.

The end of Google as we know it?

Based on news reports, Google is viewing chatbots as a threat. Here’s the problem: When you ask Google a question, you get the “long answer.” The long answer comprises a series of links that Google thinks may contain the information you’re looking for.

But if you type the same query into a chatbot, you get the “short answer” summarized right from the get-go. There’s no fooling around with links and endless resources. You immediately get the answer the chatbot thinks answers your question (although it may be incorrect).

Supposedly, Google is working on the problem of how to provide more immediacy so it doesn’t lose market share to chatbots. However, they’ve already been working on it for quite a while. [Editor’s note: This is already in place.]

If I open an incognito window on my computer (to minimize the effect of my personal search preferences) and search for “winter bees vs summer bees,” I see the following on the Search Engine Results Page: a featured snippet at the top, followed by a list of questions that “People Also Ask,” and finally the search results, which is the list of links that Google believes best answer the question.

On the day I searched for “winter bees vs summer bees,” the first entry in the list section (the long answer) leads to an article I wrote for Countryside magazine followed by 31 million other results. But the paragraph at the very top of the page, also known as the Featured Snippet, leads to an article on my website. One partial sentence in the snippet is boldfaced, not by me but by Google. It reads, “winter bees are workers that emerge near the end of the foraging season.” Why Google highlighted that partial explanation is not clear to me because it doesn’t begin to define a winter bee. I find it embarrassing.

But here’s the point: Featured snippets for any Google search used to be rare, but now they appear in about 70% of searches. I’ve also read that a majority of searchers read the featured snippet and nothing more. They get the “short answer” (no matter how truncated) and feel satisfied.

Be careful when learning beekeeping from a chatbot. This AI-generated bee sees a problem.
Be careful when learning beekeeping from a chatbot. This AI-generated bee sees a problem.

Consider the source

I think that all this truncated learning, whether it comes from chatbots, featured snippets, or Facebook posts, is dangerous and sad. Apparently, in-depth learning is too much trouble, so we take a short phrase from context and call it “truth.”

The scariest thing about AI writing is the way chatbots learn. ChatGPT claims to write answers based on internet learning. But as we all know, misinformation is rampant on the net. If chatbots learn from the internet and can’t understand or analyze what they read, why do we expect the information they generate to be any better? Remember the old saying, “Garbage in, garbage out”?

During high school, my snarky friends and I would snicker and hiss, “Consider the source!” when someone we didn’t like had something to say (not one of my finer moments). But today, I would like to shout that same advice from the rooftops: We need to consider the sources of our information. We can’t just accept the top bot-selected five-word answer to everything, regardless of whether it’s a chatbot or a Googlebot.

How can you identify chatbot writing?

I can guarantee without a moment’s doubt that beekeepers will soon see plenty of AI-generated blog posts and YouTube scripts. I even had one on my website (remember that dark and dreary day?) but I had to rewrite about 90 percent of it. The wording was so flat and boring, I couldn’t use it without tweaks and twists and a general overhaul.

Programs are now available that can detect “bot talk,” but if you’re in a hurry, I assembled a few personal tips for deciding if a human or a machine wrote a document:

  1. AI writing tends toward the mechanical and formulaic. Human writing is more varied with pinches of personality, stupid jokes, eye-rolling puns. And if you enjoy alliteration or a sprinkle of asyndeton, you won’t find it in AI.
  1. Although AI language models are improving, they make plenty of mistakes that humans do not. You may notice errors in grammar, spelling, or punctuation that are unusual for a human writer to make. On the other hand, AI doesn’t make typos.
  1. AI-generated text may be less coherent and may not flow as naturally as human-written text.
  1. AI models may generate repetitive sentences or phrases, especially after the first few paragraphs. After a bot runs out of things to say, it likes to reword and repeat.
  1. AI text may incorporate dubious or fishy logic.

How to stuff smoke back into a smoker

At one point, I asked the chatbot what equipment every new beekeeper needs. It gave me a long list of obvious objects, including a smoker. However, it included the following shifty warning:

“Smokers are used to calm bees and make it easier to work with them. However, the smoke produced by the smoker can carry diseases and pests from one hive to another. It is best to use a separate smoker for each hive to reduce the risk of cross-contamination. If a beekeeper uses the same smoker in multiple hives without properly cleaning and disinfecting it, the smoke produced by the smoker can carry diseases and pests from one hive to another.”

Seriously? I’m supposed to disinfect my smoker between hives because infected smoke might crawl back into the can after wafting through an infected hive? Who knew smoke could be so conniving?

I worry about who may read this stuff. If suddenly we see beekeepers heading into their apiaries with flatbeds piled high with smokers, you’ll know the source of that advice.

I’m still trying to understand how all that contaminated smoke gets back into the smoker. Pixabay
I’m still trying to understand how all that contaminated smoke gets back into the smoker. Pixabay

The future of learning beekeeping from a chatbot

Personally, I think AI writing will get better. The programs haven’t been around long, and they will not get worse. In fact, it seems they have only one way to go.

But for now, readers must beware. In my searches, I’ve found lots of suspicious blog posts, especially on sites that are simply trying to sell the equipment of the day. They want to look like real blogs, but the text is just filler — something to keep the ads from interfering with each other.

The last question

After a couple of hours of AI amusement, I became frustrated and bored. In despair, I asked one last sarcastic question. To my surprise, I got a logical answer.

Me: How many beekeepers does it take to change a light bulb?

Chatbot: It is not a common task for beekeepers to change light bulbs, as bees do not require artificial light to thrive. However, if a beekeeper did need to change a light bulb, it would only take only one beekeeper to do so.

Enough already.

Rusty
Honey Bee Suite

About Me

I backed my love of bee science with a bachelor’s degree in Agronomic Crops and a master’s in Environmental Studies. I write extensively about bees, including a current column in American Bee Journal and past columns in Two Million Blossoms and Bee Craft. I’ve endured multiple courses in melittology and made extensive identifications of North American bees for iNaturalist and other organizations. My master beekeeper certificate issued from U Montana. I’m also an English nerd. More here.


Discover more from Honey Bee Suite

Subscribe to get the latest posts to your email.

7 Comments

  • The chatbot took that smoker-cross-contamination concept directly from some human’s paragraph about hive tools, filed off the serial numbers, and swapped in smokers. That’s plagiarism.

    For my purposes, I don’t need to identify chatbot writing. If the chatbot learns to write as sensibly and entertainingly as you, I’ll just add it to the sites I read. If a chatbot or a human is writing dull and stupid stuff, I quit reading.

    Also, you made me look up a word that wasn’t even specialist entomology jargon, but I’m pretty sure I’m not going to remember ‘asyndeton’ if I ever need it.

    • Roberta,

      You will probably never need it, just like the rest of us. But I like it. Whenever I use asyndeton (or polysyndeton) my grammar checker has heart failure and splashes red ink all over my work.

  • Thank you for the word “asyndeton,” with which I was unfamiliar.

    I like to remind people that ChatGPT is a very sophisticated plagiarist, since it has no original ideas.

    • Diana,

      You are right on. I have found the chatbots using lists and entire paragraphs from my posts verbatim and not even linking back to my site. It makes me wonder if I should keep writing. If the chatbots just copy what I write, will I at some point be blamed for copying them? Probably.

  • I noticed this morning that a large amount of bees have congregated on the front of my bottom deep. I have a fairly large colony this year almost filling two deeps. They have a bit more to fill in the top deep and we will be placing the honey super. Any ideas on the large amount on the front of the hive. I would guess at least 300 bees. It’s 80°. With slight humidity. Normal?

Leave a Comment

This site uses Akismet to reduce spam. Learn how your comment data is processed.