Many of my colleagues fear ChatGPT. They fear that students will use this new online tool based on artificial intelligence to generate papers and answer questions on homework assignments that students are meant to tackle themselves. Their fear is legitimate. Why? Because if you read ChatGPT’s answers to a range of questions, you notice something rather quickly. ChatGPT generally produces plausible, thoughtful, coherent responses. Furthermore, ChatGPT writes well — at least compared to what I see from most of my undergraduate students. In short, ChatGPT creates headaches for instructors. It is forcing us to reconsider how we evaluate our students.

On the other hand, I was excited to learn what this new AI tool would produce when asked about loon biology. I asked ChatGPT: “Do loons mate for life?”. It responded:

While common loons often return to the same breeding territories and may reunite with the same mate from the previous year, these pair bonds are not necessarily permanent. After the breeding season, loons typically migrate to coastal or open water areas for the winter, and their social behavior can be more flexible during this time. When they return to their breeding territories in the following spring, they may or may not reunite with the same mate.

Now, this is not a terrible answer. ChatGPT is correct when it suggests that loons do not mate for life. But its mention of migration is off-topic. Its point regarding “social behavior” during winter is irrelevant. Its statement that loons “may or may not reunite with the same mate [in the spring]” is grossly misleading. And ChatGPT has entirely failed to mention the chief reason why loons do not mate for life: territorial eviction.

ChatGPT’s responses to loon-related questions are similar to its answers on other topics. The program searches the web for information from which to build its responses. But because these responses draw information from countless online sources, they include the good, the bad, and the ugly. In short, ChatGPT gives you a blur of “conventional wisdom” about any topic, not rigorous and precise scientific truth. Its answers are, for the most part, uncontroversial, vague, and riddled with caveats.

I turned my attention to loon conservation. When I asked, “Are any common loon populations in trouble?”, ChatGPT came back with:

As of my last knowledge update in September 2021, the status of loon populations, particularly the Common Loon (Gavia immer) in North America, varied by region and was a subject of concern in some areas. Common Loons were classified as a species of “Least Concern” by the International Union for Conservation of Nature (IUCN) due to their relatively stable population at the global level.

However, it’s important to note that local and regional populations can face significant challenges, including habitat loss, water pollution, lead poisoning from ingesting fishing tackle, disturbance from boating and recreational activities, and climate change impacts on their breeding and wintering grounds. These factors could affect specific loon populations and lead to localized declines.

ChatGPT is spot on in some respects. Loons are in no trouble globally. And the status of populations varies from one region to another. But the program uncritically lists many anthropogenic factors that might harm loon populations and provides no specific information. One might infer from ChatGPT’s statement that we must solve all of the problems listed in order to preserve loons. Or perhaps loon populations face many obstacles but none is severe enough to cause serious harm. In truth, we do not know which, if any, of the listed factors might endanger loons. Furthermore, ChatGPT has failed to mention two factors — exploding black fly populations and decreased water clarity — known to harm loon populations in the Upper Midwest. If this had been a class assignment, ChatGPT would have earned a “C-“.

ChatGPT’s take on factors threatening loons sounds eerily familiar to what we loon conservationists often say. (I include myself in this group.) That is, we often settle for a ChatGPT-caliber pronouncement about loon conservation. We say or imply that if we: 1) enact a lead ban, 2) reduce human settlement on northern lakes, 3) eliminate water pollution, 4) keep boaters away from adults and chicks, and 5) halt climate change, then we can save loons. These goals, of course, range from difficult to impossible to achieve.

A ChatGPT-like approach will not save loons. We simply cannot eliminate all threats. In fact, many factors that loon conservationists perceive as threats pose little or no hazard. The best example is human recreation. While lead sinkers are a danger to loon populations because of the many breeding adults they kill each year, loons are well-equipped to handle boaters. Loons tremolo, wail, or yodel when boats are too close to them or their chicks. They penguin dance, charge, and dive noisily at boats that creep close to their nests. Humans usually interpret these warnings correctly and back away in short order. Moreover, the low rates of mortality and nest abandonment attributable to boating activity indicate that loons tolerate human interactions well.**

How do we distinguish between relatively benign environmental factors, like boating, and those that truly endanger loon populations, like black flies, lead sinkers, and water clarity? Science. Only science will save loons. If the Minnesota loon population is declining and 50% of loon deaths result from lead poisoning, the folks in Saint Paul will take notice. If Wisconsin loons fledge 40% fewer offspring nowadays than in 1995 because of lower water clarity, that will make headlines in Milwaukee. And if the fledging rate across the Upper Midwest is 30% lower owing to black fly-induced nest abandonments, that might turn apathy concerning climate change into action.***

So if you are an unprincipled student being taught by an inattentive instructor, ChatGPT might earn you a “B” on your history paper. And if you cannot get the wording right in a letter to a client or colleague, ChatGPT might provide suggestions. But we loon conservationists should resist the uncritical, shotgun approach that ChatGPT takes to addressing questions. If we are going to preserve loon populations that we treasure, we must first collect data. And then, in our communications with the public, politicians, and the media, we must highlight the specific environmental hazards that science has shown to be dangerous to loons.


* The featured photo was taken a week ago by Linda Grenzer of an adult male from Lake Winter, Wisconsin that swallowed a lead sinker. Though the sinker was surgically removed by Raptor Education Group in Antigo, the male died two days later from the lead it had already absorbed.

** I might be biased by my work in Wisconsin and Minnesota in my conclusion about loons coping with boating activity. It is conceivable that boats do cause enough nesting failure and/or chick mortality in some regions to threaten loon populations. We do not have data to show such a pattern, however. If you know of such data, please let me know.

*** I made up these three numbers. We are still collecting data on loon mortality caused by lead sinkers. Only recently have we learned about the threats of black flies and loss of water clarity. We and our partners are recording many lead-poisoned loons these days. We will publish an estimate of lead’s impact within five years. Robust estimates of the impacts of black flies and water clarity on loon populations in Wisconsin (and possibly Minnesota) should be available by sometime in 2025.

The past month and a half have been a roller coaster ride, though mostly downwards. Six weeks ago I learned that major funding for my field work in Minnesota had dried up. I cursed my luck. I scratched my head. A thousand “what ifs” passed through my brain.

But looking back was pointless. In time, my mind began to turn to one cheerful and unassailable fact. Loon Project field teams in 2021 and 2022 had given their all to expand our database into a new state where, initially, we knew almost no one. As we began to meet the warm, supportive, loon-loving folks of Minnesota, we gained momentum. The National Loon Center provided tons of support, financial and logistical. New friends shared boats, gave us access to private lakes, towed our capture boat from lake to lake in the middle of the night, or simply drove us around in their own boats during capture to help us find and mark breeding loon pairs. Kevin Kenow and his USGS colleagues spent six long nights in 2022 capturing loons to swell our study population. When the dust settled in early August of last year, we were well over halfway to our goal of establishing a Minnesota Study Area on par with our traditional study area in Wisconsin.

That we have not been diverted from that path is a tribute to our great pool of friends and supporters in Wisconsin, Minnesota, and across the U.S. One day a few weeks ago was a first turning point. An anonymous friend from Wisconsin pledged $7,000 “to support the Minnesota part of the Loon Project”. I was touched that someone in Wisconsin trusted me with this gift, and moreover, dedicated it not to the loons of their own state but to those of an adjacent one. *

Just yesterday, another group of donors from Minnesota helped us reach another turning point. Roger and Phyllis Sherman, Don Salisbury, and Gwen Myers have together contributed $21,000 to the Minnesota Loon Project to establish the Judith W. McIntyre Fund to support our work in the state.

It is a great honor to feel that I am building upon Dr. McIntyre’s seminal work on loons, which took place in Minnesota, Saskatchewan, and Upstate New York. Judy had a gift. She did robust, impactful science that taught us a great deal about loons. At the same time, she was able to convey her passion for loons and loon conservation in a charming, down-to-earth manner that reached the public. I have a dog-eared copy of her classic book, “The Common Loon: Spirit of Northern Lakes” on my shelf to which I often refer. When I think back to my interactions with Judy, though, what I remember most vividly is the warmth and humility with which she welcomed me to the fellowship of loon biologists back in the mid-1990s. She viewed the study of loons as a calling to which all could aspire — even the young whippersnapper that I then was.

The new Judith W. McIntyre Fund is a timely and exciting development. This gift adds to the dozens from other supporters of the Loon Project from Alaska to Colorado to Maine who have stepped up to donate during our time of greatest need. And I cannot forget other folks who have provided the Loon Project team with lodging in Wisconsin (especially Skip and Ruby, Mary, and Linda and Kevin) and Minnesota. Friends and supporters have truly kept the Loon Project afloat in recent years. Gifts earmarked for Minnesota have now brought us right back to where we were before the loss of funding six weeks ago. In other words, thanks to all of you, our goal of producing a robust population model for loons in north-central Minnesota is back on the horizon.

Since I view many events in my life through the prism of my study animal, I cannot help but recall at this moment the plight of the former male loon on Jersey City Flowage, near Tomahawk, Wisconsin. (See Linda Grenzer’s photo of him, above.) Banded as a chick on Swamp Lake (9 miles away) in 1995, “Red/Red, Red/Silver” had easy-to-read bands and a relaxed disposition to match. During each spring for over a decade, I looked forward to seeing his bright color bands under the surface as he permitted us to approach him closely for identification. But he was suddenly at death’s door in June of 2014 after swallowing two lead sinkers attached to a fishing line. If not for the quick and professional work of the Raptor Education Group, he would have been doomed to a slow and painful demise. The REGI folks removed the sinkers, patched up his lacerated tongue, fed him all of the suckers he could swallow, and quickly got him back in the water. Defying the odds, R/R,R/S recovered his lost body mass, migrated southwards in the fall of 2014, and returned to breed the following April, as laidback as ever. He must have felt then as I do now.

I know what you are thinking: another feel-good story of overcoming adversity that features loon/human parallels! Now that we are back in business in Minnesota, perhaps I will plague you less often with such tedious anecdotes. But things have been going pretty well lately. So I can’t make any promises.


* As I noted in an earlier post, research in our traditional Wisconsin Study Area will proceed as before. That is, we will continue to build the Minnesota Study Area without compromising our productive long-term study of loons in Wisconsin.

Ensconced as I am in the endless summer of southern California, it is easy for me to forget what loons are facing. As we know from Kevin Kenow’s excellent work, about half of all adults have now left their breeding lakes in Minnesota and Wisconsin and are on their way southwards. Many of these birds are hanging out in the Great Lakes before making the long overland journey to Florida. Some adults remain faithfully with their chicks, hoping to stuff a few extra fish into them before abandoning them to their own devices.

Adults’ departure leaves only chicks on the breeding grounds. Thanks to the the work of our fall observation teams and Brian Hoover, who pulled the data together and wrote it up, we know that most juveniles leave their natal lakes in the fall but hang out nearby. They search diligently for large, food-rich lakes, especially favoring those that resemble their natal one in pH. Their strategy is clear. First, stuff your face with fish where they are abundant and similar to the ones you first learned to hunt. Next, wait until the last possible minute to build up your energy stores. Finally, bolt for Florida before the ice makes it impossible to take off.

The juveniles’ plan has a touching pragmatism to it. There is no subtlety. Birds of the year are not burdened with territorial responsibilities or pangs of parental guilt. They just wish to survive long enough to reach the wintering grounds. And, generally speaking, they do.

But a few get left behind. Thus it happened with the Lake Thompson juvenile this fall. A great strapping youngster when we caught him in late July at five weeks of age, he continued to grow and thrive in the 12 weeks since we last saw him. Ultimately, he had no more need of his parents and moved five miles west to Boom Lake in Rhinelander to fatten up for migration. There, however, he ran afoul of a reckless hunter. Linda and Kevin Grenzer caught him last night and quickly saw that his left wing was fractured. X-rays at REGI confirmed the break — caused by goose shot visible in the x-ray.

I cannot think what else to say.


Top photo by Linda Grenzer. X-ray by REGI staff.