Date: 4/20/26 3:21 pm From: Dennis Paulson via Tweeters <tweeters...> Subject: Re: [Tweeters] The Merlin discussion
Bill, thanks. That was a wonderful account summarizing Merlin and its value.
My most fervent and constant hope for all that AI gives us is that it won’t reduce our ability to think very much. Published accounts show that it is indeed doing just that in some areas, and let’s try not to have that happen in birding. Just as I’m sure you did, I had to exercise a lot of brain cells to learn how to identify birds from sight and sound, and when an app does the work for me, I’m not exercising those neurons!
And to add something about birds, we still have at least one beautiful male (Audubon’s) Yellow-rumped Warbler coming to our feeders, after all the other migrants (Orange-crowned and Townsend’s Warblers, Golden-crowned, White-crowned and Fox Sparrows) have deserted us. I hope more are on the way.
Dennis Paulson
Seattle
> On Apr 20, 2026, at 1:33 PM, Bill Tweit via Tweeters <tweeters...> wrote:
>
> The Chipping Sparrow/Dark-eyed Junco discussion has been quite informative; I’d like to offer some thoughts about some aspects of Merlin that have come up in the conversation.
>
> Everybody seems to agree that Merlin is simply a tool, but then discussions range well beyond that in terms of expectations and limitations. Merlin’s inability to accurately discriminate between CHSP and DEJU is a great opportunity to examine some of our expectations about Merlin, and determine whether they are realistic. First, why do we expect Merlin to be any better than a reasonably skilled human observer? It is trained by humans, so it seems unlikely that it would do better. And reasonably skilled human observers, a category I consider myself to be in, routinely experience difficulty separating those two species, for very good reason. Junco songs are notoriously diverse, the range of trill diversity has already been discussed well. They also buzz, and on one occasion I actually encountered a male junco singing a perfect Clay-colored Sparrow song. Dashed my hopes when I saw it. Bottom line, please do not expect Merlin to be perfect, even in North America where it is quite good. Expectations should be even lower in other parts of the globe, but it does have utility in most areas.
>
> Second, why do we think that use of Merlin has increased the level of error in the eBird data? There has always been a certain level of error in the data, and I’ve not seen any evidence that Merlin has either increased or decreased that level. As a reviewer, I have seen “identified by the field trip leader” as documentation for many years, which is just as flimsy documentation as “identified by Merlin”. In both cases, a reviewer will almost always request the observer to include actual details that will meet eBird standards for acceptable documentation. And, in most cases, a reviewer will see it as an opportunity to provide some coaching to contributors on providing defensible documentation. If the observer chooses not to provide documentation, then it will not be included in the public database, which is where error matters. If it is a sighting that doesn’t require documentation, it will be included in the public database, which is well-understood to have some low levels of error that requires the use of statistical tools that are good at detecting signal amidst some noise, or what we call misidentifications.
>
> Merlin has undoubtedly helped increase the number of new or novice birders, but is there any evidence that it has changed the ratio of novice:skilled birders? I’ve not seen such evidence, and my subjective assessment is that the wave of new birders has been simultaneous with a significant increase in the number of proficient birders. If the ratio has been relatively constant over the span of eBird years, then Merlin has not increased the magnitude of error in the database.
>
> And, let’s not forget that Merlin was built to assist with several objectives, only one of which is helping birders in the field. It has another, very significant, purpose: to increase awareness of birds among the general population. Most of the Merlin users I encounter now are people who take some joy in finding out what birds are present in their yard, or on the favorite walking routes, or while they are camping, … They aren’t contributing sightings to eBird, they just want to know more about the world around them. It definitely increases environmental awareness, an entirely separate purpose than helping birders. And an immensely valuable function. Does it matter to them if Merlin is imperfect in some ways? Not really. They are just excited and appreciative to put a name on a mysterious singer, or know that there are at least 15 species of birds on their morning route. A third purpose is to make birding more accessible for people with disabilities, and I have had several chances to speak with people who always enjoyed birds, but found that increasing physical limitations was making it harder for them to still find pleasure in it. They demonstrated how they use Merlin to restore some of their ability to find and experience birds. I don’t know of any statistics on the proportions of Merlin users who fall into each category, but in my everyday, non-birding world, I am consistently surprised by the number of people who are not birders but are fans of Merlin. Without hard data, I wouldn’t want to make any assumptions about levels of birder vs non-birder use.
>
> So, let’s be realistic about Merlin. It’s a great tool, but it is just a tool. Learn it’s limitations in your area, and enjoy it’s strengths. Kudos to Carol R. for reminding folks that junco/Chippy confusion is one of those limitations, and offering some tips on how to address it. Don’t expect Merlin to be super human. And remember, it wasn’t designed just for eBirders. And, as everyone has said, please, please, please confirm your detections of unusual birds with more tools than just Merlin.
>
> Bill Tweit
>
> Olympia, WA
>
>
>
> _______________________________________________
> Tweeters mailing list
> <Tweeters...>
> http://mailman11.u.washington.edu/mailman/listinfo/tweeters
