A ChatGPT case study: List of cicada species in New Jersey

I make plenty of errors. I fix some. Some I leave because imperfections make life more interesting. Imperfections allow us to change, adapt and evolve. My cicada blog Cicada Mania has plenty of errors. It has grammar errors, it has speculation and theorizing that deviates from fact, it has mobile usability issues Google demands that I fix, and it has old facts, once true, that are now false. I use Grammarly to check my grammar and spelling as I write. Often I find myself disappointed with its corrections because I feel it removes some of the flavor and improvisation of my writing. It kills the jazz. It deodorizes the funk. So I ignore it.

When looking into ChatGPT, I look at its responses through a human eye. I think I can see where its errors come from — they come from humans not tuning the AI and errors — like those mentioned above — that come from old and outdated sources. So, the answers it provides can be a little funky and a little wrong. I would not use ChatGPT to write a paper that needs to be 100% correct — maybe the outline of a paper and then do my own research, fill in the gaps and verify the data with multiple sources.

I tested ChatGPT‘s knowledge using a topic I’m very familiar with, “cicada species in New Jersey”. I hope to discover the limits of its knowledge and speculate where and how it fails to deliver a perfect answer. I encourage you to do the same with a topic you are very familiar with.


  • When it comes to cicadas (living insects), ChatGPT provides the binomial nomenclature, common name, and emergence frequency of each cicada. I was impressed with the inclusion of emergence frequency in its knowledge graph for cicadas, as emergency frequency is an important aspect of cicadas, whereas location, binomial nomenclature, and common name are applicable to all forms of life.
  • ChatGPT is unaware of recent changes to the binomial nomenclature of many North American cicadas (Hill, 2015) (Sanborn, 2008). Perhaps it is learning from older publications & web pages — like a 15-year-old article on my website. My advice to ChatGPT would be to check recent documents when it comes to the binomial nomenclature of insects, and life in general.
  • ChatGPT got several common names wrong. I imagine that this happens by learning from incorrect information on the web, getting information mixed on from a single web page, or when reading a category or tag page on a blog that cuts across multiple topics (in this case, multiple cicada species).
  • ChatGPT put two cicadas in the list that are not found in New Jersey. The inclusion of Neotibicen superbus cicadas was way off — that cicada is located in and around Texas. The inclusion of Neotibicen pruinosus was respectable because prominent documents place Neotibicen pruinosus in New Jersey, but it is really its sister species Neotibicen winnemanna that is found in New Jersey, with Neotibicen pruinosus existing west of the Appalachians.
  • I would give ChatGPT an overall grade of C. All the lifeforms in its lists are cicadas, 80% are found in New Jersey,

ChatGPT response

Remarking on ChatGPT’s response to “List of cicada species in New Jersey” line by line:

Cicadas are a group of insects known for their loud mating calls. There are several species of cicadas that can be found in New Jersey, here is a list of some of them:

So far, ChatGPT is correct. Grade A.

1. Magicicada septendecim: known as the “17-year cicada” it emerges in large numbers every 17 years.

  • Correct location.
  • Correct binomial nomiclature.
  • Correct common name.
  • Correct emergence frequency.

Grade: A+ (100/100).

Trivia: Magicicada septendecim is also known as the Pharoah Cicada.

2. Magicicada cassini: known as the “13-year cicada” it emerges in large numbers every 13 years.

  • Correct location.
  • Correct binomial nomiclature.
  • Incorrect common name. “17-year cicada” and “Dwarf Cicada” would be the correct answers.
  • Incorrect emergence frequency. Magicicada cassini emerges every 17 years.

Grade C- (70/100).

Trivia: There is a similar species named Magicicada tredecassini that has a 13-year lifecycle, but it is not found in New Jersey. More information about Magicicada cassini.

3. Tibicen canicularis: known as the “dog-day cicada” it emerges every year.

  • Correct location.
  • Incorrect binomial nomiclature. Tibicen canicularis has been known as Neotibicen canicularis since 2015 (see Hill 2015).
  • Correct common name.
  • Correct emergence frequency.

Grade: A- (90/100).

Trivia: more info about Neotibicen canicularis.

4. Tibicen chloromera: known as the “green-faced cicada” it emerges every year.

  • Correct location.
  • Incorrect binomial nomiclature. Incorrect genus (Hill, 2015) and species (Sanborn, 2008).
  • Possibly a correct common name. Popular common names for Neotibicen tibicen are “Swamp Cicada” and “Morning Cicada”. I’ve never heard of the name “green-faced cicada”, but I do not have evidence to the contrary, so I cannot dispute this. Interestingly enough, chloromera comes from the Greek words meaning “green thighs”. Certainly both its legs and face can be green.
  • Correct emergence frequency.

Grade B- (80/100).

5. Tibicen linnei: known as the “Linne’s cicada” it emerges every year.

  • Correct location.
  • Incorrect binomial nomiclature. Tibicen linnei has been known as Neotibicen linnei since 2015 (see Hill 2015).
  • Correct common name.
  • Correct emergence frequency.

Grade A- (90/100).

6. Tibicen tibicen: known as the “harvest fly” it emerges every year.

  • Duplicate entry!
  • Incorrect binomial nomiclature. Tibicen tibicen has been known as Neotibicen tibicen since 2015 (see Hill 2015). Note there are two subspecies.
  • Correct location.
  • Debatable common name. Harvest fly, Dog-Day Cicada, or Jar Fly, are common names for all Neotibicen and Megatibicen cicadas in general, but Swamp Cicada and Morning Cicada are the names popularly used for this cicada.
  • Correct emergence frequency.

Grade C- (70/100).

7. Tibicen lyricen: known as the “northern dusk-singing cicada” it emerges every year.

  • Correct location.
  • Incorrect binomial nomiclature. Tibicen lyricen has been known as Neotibicen lyricen since 2015 (see Hill 2015).
  • Incorrect common name. The correct common name for this cicada is Lyric Cicada. There is a “northern dusk-singing cicada” in New Jersey, but that species is Megatibicen auletes.
  • Correct emergence frequency.

Grade C (75/100).

8. Neotibicen pruinosus: known as the “pruinose cicada” it emerges every year.

Grade: D- (60/100).

9. Neotibicen superbus: known as the “superb cicada” it emerges every year.

  • Incorrect location. This cicada is not found in New Jersey. It is found in Texas and surrounding states.
  • Correct binomial nomiclature.
  • Correct common name.
  • Correct emergence frequency.

Grade: D- (60/100).

10. Okanagana rimosa: known as the “eastern cicada” it emerges every year.

  • Correct location.
  • Correct binomial nomiclature.
  • Possibly a correct common name. The popular common name for this cicada is Say’s Cicada. I’ve never heard of “eastern cicada” applied to this species, but it may be correct.
  • Correct emergence frequency.

Grade: A- (90/100).

It’s worth mentioning that this list is not exhaustive and there may be other species of cicadas found in New Jersey, also the emergence of cicadas is affected by weather, temperature, and the health of the population, so the emergence of some species may vary from year to year.


Grade: A.

Again, overall ChatGPT gets a C.

Grading scale:

  • Is the location correct (New Jersey)? 40 points.
  • Is it a cicada? 15 points.
  • Is the binomial nomenclature correct? 15 points.
  • Was the binomial nomenclature correct at one time? 5 points.
  • Is the common name the most popular common name? 15 points.
  • Is the common name a lesser-known common name? 5 points.
  • Is the emergence frequency correct? 15 points.
  • Duplicate entry penalty: -5 points.

  • 2015 Neotibicen cicada name change document: Hill KB, Marshall DC, Moulds MS, Simon C. Molecular phylogenetics, diversification, and systematics of Tibicen Latreille 1825 and allied cicadas of the tribe Cryptotympanini, with three new genera and emphasis on species from the USA and Canada (Hemiptera: Auchenorrhyncha: Cicadidae). Zootaxa. 2015 Jul 10;3985(2):219-51. doi: 10.11646/zootaxa.3985.2.3. PMID: 26250031.
  • 2008 chloromera to tibicen name change document: Allen F. Sanborn “The Identity Of Cicada tibicen Linné [=Tibicen chloromerus ()] (Hemiptera: Cicadoidea: Cicadidae),” Entomological News 119(3), 227-231, (1 May 2008).[227:TIOCTL]2.0.CO;2
Sony ILCE-7M3

Buckeye Butterfly photo taken with a Sony ILCE-7M3

This is a photo of a Buckeye Butterfly Buckeye taken with a Sony ILCE-7M3 and Sony’s 100mm macro lens.

ILCE-7M3 is the other name of the Alpha 7iii camera. Buckeye


I should gave gotten the R version of the camera for the extra MBs. Photography can be an expensive hobby, both in terms of money and time (learning to properly use the equipment).

I began my photography hobby in the 2010s to get close-up photos of insects & plants. I bought a quality camera, a macro lens, a tripod, and lights. What I did not know about was “focus stacking”, the process photographers use to stack many photos taken with slightly different focus settings to create a single in-focus image. I would take photos with my macro lens and think, “why is only one part of the photo in focus”, “is it an aperture issue”, or “do I just suck and photos”? Nah — the secret is photo-stacking in Photoshop.

The images on this page are not focus-stacked.

I expect in-camera firmware to auto-stack photos in the future. The phone or camera company that comes up with that will be a winner.


Nikon D7200

Green Darner Dragonfly taken with a Nikon D7200 and a Tokina AT-X M100 PRO D

This Green Darner Dragonfly photo was taken with a Nikon D7200 and a Tokina AT-X M100 PRO D. One of my favorite photos taken with that lens/camera combination. 
Green Darner
Dragonflt Closeup D7200

Nikon D7200

Skipper butterfly taken with a Nikon D7200 and a Tokina AT-X M100 PRO D

This is a skipper photo taken with a Nikon D7200 and a Tokina AT-X M100 PRO D.

Nikon skipper

I updated the firmware on my cameras. Getting ready for the spring and summer.

Skipper Close up


10 Volcanoes in New Jersey?

One of my new hobbies is rock collecting and geology. Rock collecting (or rock observing where collecting is not allowed) is a relatively cheap hobby, and it gets me out of the house which is healthy for the mind and body.

New Jersey is famous for fluorescent minerals, like willemite, found in the Franklin, New Jersey area. I was thrilled to learn that New Jersey has fluorescent minerals outside of the Franklin area, like sodalite in the Beemerville nepheline syenite mass. Around the same time I learned of the sodalite, a family member sent me a link to a story about the New Jersey volcano, Rutan Hill.

I downloaded Google Earth and installed a KMZ file of New Jersey geological data to check out the volcano and the nepheline syenite mass where the sodalite is found.

The pink areas are the nepheline syenite, the red areas are ouachitite breccia, and the “R” is the Rutan Hill volcano. The USGS page about ouachitite breccia says it is found chiefly “in numerous diatremes in the Beemerville area; largest of at Rutan Hill.” Diatremes, “are sometimes known as a maar-diatreme volcano” (quoting Wikipedia). If Rutan Hill is a diatreme volcano, the rest of the red areas below are probably also diatremes. Counting the red areas on the map, there are 10 “volcanos” in New Jersey. Not active volcanos, but old ones nonetheless. Cool. Now I want to buy a house on one of them. Interestingly, Grammarly wants me to change “on” to “in”. I don’t want to live “in” a diatreme, Grammarly.

10 Volcanoes in New Jersey

You can see some of these features in Lidar data as well. This is not the same scale and area as the Google Earth map:

Lidar Hillshade


ChatGPT & AI link list

I should have asked ChatGPT for a list. 🙂

Not ChatGPT

Stuff I don’t understand yet:

  • Pinecone.
  • Machinet. “Code faster, reduce mistakes, and take your team to the next level.’

10 of my favorite tools

When you think about tools hammers, screwdrivers, saws, and wrenches probably come to mind, but virtually anything can be a tool as long as it helps you achieve a goal.

This is a list of 10 of my favorite tools that I use every week.

#1 – small notebooks. The brand doesn’t matter as long as they don’t fall apart. The one in the picture is from Tom Sachs. Sure you have a phone and/or computer to take notes, but you should have a paper backup. And they’re hacker-proof.

10 Bullet Notebook

#2 – pens taken from hotels. These are free. You’ll find one in your hotel room. You can get more from the lobby. Tip: hotels also have free soap, lotion, and notepads.

Hotel Pen

If you’re looking for a pen without a hotel logo, that can also write upside down, I recommend the Fisher Space Pen:

Space Pen

#3 – Sharpies. It’s hard to go wrong with Sharpie markers.


That said, you need Staedtler markers too. These you use specifically for writing on DVDs and CDs because they are friendlier to the surface of the media.


#4 – Gaffer Tape. Not cheap, but I use it for everything. I started to use it to secure computers and measurement equipment in my car, but I’ve replaced masking and duct tape entirely with this stuff.

  1. It sticks to almost everything.
  2. It is temporary — little to no residue, unlike duct tape.
  3. It is matte, not shiny.
  4. It comes in fluorescent colors.

Gaffer Tape

#5 – toothbrushes. Once I retire a toothbrush from tooth duty, I wash it in the dishwasher and then use it for everything else. Car detailing, brushing dirt off of mineral specimens, cleaning the bathroom sink, as a tiny brush for my eyebrows…


#6 – dental picking tools. You can get these new from the usual online stores and auction sites. Normally they’re used for teeth, but I use them for detailing, cleaning mineral specimens, and cleaning dust and grime out of tight spaces in electronic equipment. I’m thinking of asking my dentist for the tools they use on my mouth once they’re done with them.


#7 – Tea Tree Therapy toothpicks. I like both kinds: mint and cinnamon. They’re good for cleaning your teeth on the go, but they’re also a decent gum or cigarette alternative, and you can use them for detailing and cleaning tight spaces where you don’t want to use a metal pick. Plus, A Toofpick Changes Everything.

Tea Tree

#8 – OLFA razor knives. These are my go-to cardboard slashers and envelope openers. When I need to turn an old couch into 47 small pieces, I start with an OLFA (and end with a saw & bolt cutter). I have similar razor knives like the Milwaukee Fastback as well, but OLFAs are my favorite.


#9 – cigar boxes. Most cigar stores will sell you these for a few bucks. If you’re charming, you can get them for free. I use these to hold mineral specimens & tools, but you can use them for electronic equipment, tubes, screws & bolts, bugs, tiny notebooks, or whatever you want.

Cigar Box

#10 – Rubbermaid containers. I use these for collecting stuff outdoors, rocks, shells, and stuff that can be wet or dirty. Before stuff goes into cigar boxes, they go into Rubbermaid containers.


Honorable mentions:

  • Rough Rider mushroom knife with the brush.
  • Dymo label makers. The old-school kind.
  • Everclear 190 proof. For disinfecting and preserving.
  • Silica Gel packs for drying wet things.
  • Boveda humidity packs for wetting dry things.
  • Vitamins & minerals D, K, C, zinc, quercetin, melatonin, and asprin.




My favorite Geology resources

A hunk of mostly microcline feldspar from Franklin, NJ, sitting on my desk:


Listing my favorite Geology resources. Many of these are just for fun.


Nick Zentner: focuses on Washington state, but at the same time, he’s probably the best popular science educator at the moment. His YouTube channel amazes me. I’ll probably never visit Washington state again (I’ve been to Seattle twice) but I still watch all of his videos. His Baha BC series is my favorite “TV Show”.

Skye Cooley is good for information about ancient cicada tunnels in soils.

Myron Cook is good for field geology and the western United States.

Shawn Willsey has great geology 101 information and excellent deep dives on Idaho geology.

The USGS YouTube channel is great, even if you just want to watch a volcano in Hawaii erupt for hours on end.


Mindat is excellent for finding old mines and rock-hounding locations. good foundational information.

USGS Geological Maps of the US. I like importing KMZ data into Google Earth. And then I buy the paper maps on eBay.

USGS Publication Warehouse. I like downloading old documents and then buying the on eBay.

I’m in New Jersey at the moment so NJ Geographic Information Network is a great resource. As is the New Jersey Office of GIS for lidar info.

I follow some mining industry people like Peter Bell on Twitter. What they do is interesting, but I’m not after gold.

The Sterling Hill Mining Museum in New Jersey. Fluorescent rocks and zinc mining.

Franklin Mineral Museum. Fluorescent rocks and zinc mining. I’m a lifetime member.

The Franklin-Ogdensburg Mineralogical Society, Inc. (FOMS).

North Jersey Mineralogical Society is worth joining if you are in New Jersey, New York City, western Connecticut, southern New York, or eastern Pennsylvania.

ChatGPT Geology

Chatting with ChatGPT about mining and Zinc

Yesterday I was chatting with ChatGPT about New Jersey mining and zinc ore. is a better source of this information, but I was curious about ChatGPT’s knowledge.

Her response to a list of mines in New Jersey is very good, especially from the perspective of a hobbyist, historian, or local rock hound. There are active mining activities in New Jersey, but they are purposely not “well advertised”, so I cannot fault ChatGPT for not knowing about them. Mostly sand mining — sand for concrete needs to come from somewhere, and a lot comes from New Jersey. Other than Sterling Hill & the Franklin mines, I think Hibernia is worth mentioning because it is visually impressive, and it is fun to visit.

New Jersey was not a major mining state and there were a limited number of mines historically. Here is a list of some of the known old mines in New Jersey:

  1. Sterling Hill Mining Museum: located in Ogdensburg, it was a zinc mine that operated from the late 1700s to 1986.
  2. Franklin Mine (museum): located in Franklin, it was a zinc and iron mine that operated from the early 1700s to 1954.
  3. Bevans Mine: located in Andover, it was an iron mine that operated from the early 1700s to the late 1800s.
  4. Furnace Hill Mine: located in Andover, it was an iron mine that operated from the early 1700s to the late 1800s.
  5. The Mine Hill and Schuyler Copper Mine: located in Franklin, it was a copper mine that operated from the early 1700s to the late 1800s.
  6. The Copper Mine Hill: located in Mine Hill it was a copper mine that operated from the early 1700s to the late 1800s.
  7. The Morris Canal & Mining Company: located in Ledgewood it was a mining company that operated from the early 1800s to the early 1900s.
  8. The New Jersey Zinc Company: located in Franklin it was a zinc mining company that operated from the late 1800s to the mid-1900s.
  9. The Sussex Mine: located in Hamburg, it was an iron mine that operated from the late 1700s to the early 1800s.
  10. The Beemerville Mine: located in Beemerville, it was an iron mine that operated from the late 1700s to the early 1800s.

It’s worth noting that many of these mines are not in operation anymore and most of them are not open to the public. Some of them may have been converted into museums and open for visiting. Also, the information of these mines may be limited, and some others may have existed in the past but information about them is not well documented.

Historically, New Jersey was an important resource for iron, in the form of bog iron, clay for pottery, zinc, gravel, and sand for construction. Other than sand, it’s cheaper and more efficient to find these minerals and rocks elsewhere.

One challenge for the mining industry in New Jersey is most of the land is protected, or covered with sprawling residential neighborhoods, which are difficult to have removed, though in some cases I would like to. If I had Elon Musk’s type of money I would buy all of Parlin, New Jersey, and mine it for amber, clay, and lignite — maybe not mine it, just enjoy it from a rock collector perspective.

Here’s a hunk of zinc ore from Sterling Hill:

Zinc Ore

I also asked ChatGPT for a list of zinc ores. Three of them appear in the rock above.

Here is a list of zinc ores:

  1. Sphalerite (zinc sulfide)
  2. Smithsonite (zinc carbonate)
  3. Hemimorphite (zinc silicate)
  4. Calamine (hydrated zinc carbonate)
  5. Willemite (zinc silicate)
  6. Franklinite (an oxide of zinc, manganese, iron and nickel)
  7. Hydrozincite (hydrated zinc carbonate)
  8. Zincite (zinc oxide)
  9. Zinkenite (a sulfide mineral of zinc and lead)
  10. Siderite (iron carbonate) that contains zinc as impurity

Please note that this list is not exhaustive and there may be other zinc ores that have not been included here. Also, The amount of zinc that each ore contains varies greatly, depending on the location and quality of the deposit.


Top SEO platforms for keyword research, according to ChatGPT

I asked ChatGPT for a list of the top SEO platforms for keyword research. In my mind, I was thinking of the more “enterprise” platforms like Brightedge and Conductor, but I should have added more clarifying terms to my question. Her list is solid.

I personally think more about questions rather than individual keywords these days, which makes Answer the Public one of my favorite tools.

Here is a list of some popular SEO platforms for keyword research:

  1. Google Keyword Planner:
  2. SEMrush:
  3. Ahrefs:
  4. Moz Keyword Explorer:
  5. Keywords Everywhere:
  6. SERPstat:
  7. Long Tail Pro:
  8. Ubersuggest:
  9. KWFinder:
  10. Keyword Tool:

Please note, this list is not exhaustive, there may be other platforms available that provide keyword research capabilities. Also, the features and pricing of these platforms may vary, so you should research and compare them before making a decision.