Categories
ChatGPT

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come from — they come from humans not tuning the AI and errors — like those mentioned above — that come from old and outdated sources.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.

Findings:

  • 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.

Correct.

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). https://doi.org/10.3157/0013-872X(2008)119[227:TIOCTL]2.0.CO;2
Categories
ChatGPT

ChatGPT & AI link list

I should have asked ChatGPT for a list. 🙂

ChatGPT. I asked ChatGPT if it had preferred pronouns and it said “it”.

OpenAI Cookbook. A repository of example code and example prompts for accomplishing common tasks with the OpenAI API/ChatGPT.

OpenAI Examples.

OpenAI’s Github page.

Paper: Unsupervised Neural Machine Translation with Generative Language Models Only.

Hugging Face.

Stuff I don’t understand yet:

Pinecone.

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

Categories
ChatGPT Geology

Chatting with ChatGPT about mining and Zinc

Yesterday I was chatting with ChatGPT about New Jersey mining and zinc ore. Mindat.org 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.

Categories
ChatGPT SEO

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: https://ads.google.com/home/tools/keyword-planner/
  2. SEMrush: https://www.semrush.com/
  3. Ahrefs: https://ahrefs.com/
  4. Moz Keyword Explorer: https://moz.com/explorer
  5. Keywords Everywhere: https://keywordseverywhere.com/
  6. SERPstat: https://serpstat.com/
  7. Long Tail Pro: https://longtailpro.com/
  8. Ubersuggest: https://neilpatel.com/ubersuggest/
  9. KWFinder: https://kwfinder.com/
  10. Keyword Tool: https://keywordtool.io/

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.

Categories
ChatGPT SEO

Top Schema.org Vocabularies, According to ChatGPT

While I was chatting with ChatGPT, I asked her for a list of the top Schema.org vocabularies. I would give the list it produced a grade of A-, related to vocabularies that the SEO industry uses.   In context to the vocabularies that Google leverages, Person is typically an attribute of Article, and Logo, which is an attribute of Organization is now more important than Organization itself. I’m surprised WebSite (recent site name news) did not make her list.

Some links: Google’s guides to structured data, Rich Snippet text tool. Google’s guides are linked below:

Schema.org is a set of vocabularies that can be used to mark up content on a website to make it more easily understood by search engines. Here is a list of some popular vocabularies provided by schema.org:

  1. Article: used to mark up news articles, blog posts, and other similar content.
  2. Person: used to mark up information about people, such as authors, speakers, or performers.
  3. Product: used to mark up information about products, including prices, reviews, and availability.
  4. Event: used to mark up information about events, such as concerts, conferences, or exhibitions.
  5. Organization: used to mark up information about organizations, such as businesses or non-profit organizations.
  6. Review: used to mark up reviews of products, services, or other items.
  7. LocalBusiness: used to mark up information about local businesses, such as restaurants, hotels, or shops.
  8. VideoObject: used to mark up information about videos, such as movie trailers, music videos, or educational videos.
  9. BreadcrumbList: used to mark up the breadcrumb navigation on a website, making it easier for search engines to understand the site’s structure.
  10. FAQPage: used to mark up a FAQ page with questions and answers.

It is worth mentioning that schema.org provides many other vocabularies that can be used to markup different types of content, this list is not exhaustive.

Categories
ChatGPT SEO

Now that Crypto is tanking, let’s all talk about ChatGPT

Now that Crypto is tanking (or has tanked), ChatGPT is the favored topic among human SEO experts.

I asked ChatGPT for a list of top SEO blogs, and here is what it had to say:

Here is a list of some popular blogs about search engine marketing:

  1. Search Engine Land: https://searchengineland.com/
  2. Search Engine Journal: https://www.searchenginejournal.com/
  3. Moz: https://moz.com/blog
  4. Search Engine Watch: https://searchenginewatch.com/
  5. Search Engine Roundtable: http://www.seroundtable.com/
  6. The SEM Post: https://www.thesempost.com/
  7. The SEMrush Blog: https://www.semrush.com/blog/
  8. Search Engine People: https://www.searchenginepeople.com/blog/
  9. Ignite Digital: https://www.ignitedigital.ca/blog/
  10. Neil Patel: https://neilpatel.com/blog/

Please note, this list is not exhaustive, there may be other blogs with good information about search engine marketing. Also, the quality and relevance of the information provided may vary depending on the blog.