That’s not innovating

Tony and Patrick are back! Patrick is in Grand rapids attending the ATLIS conference. They will be talking about AI, innovating and how no one gives a flying hooey about the US PIRG report about Chromebooks.

As always, check out the show notes below and you can subscribe to our podcast from your very favorite podcasting app.

  1. ATLIS day 1
    1. Good workshops
    2. Innovation is not learning or using technology
    3. Grand Rapids might be nice – no idea but the weather sucks
  2. ChatGPT
    1. We are all aware that the Terms of Service require parental consent of children between the ages of 13-18 – what happens when a fair amount of people say no?
    2. Lawsuits on deck concerning intellectual property, enterprise and copyright
  3. VR questions
    1. How to model something in VR?
    2. How to send it directly to a 3D printer?
  4. Tony’s annoying AI conversation
    1. I need more info Tony
    2. Please read the disclaimers
  5. US PIRG’s Chromebook Report
    2. Nobody cares

US PIRG’s Chromebook Report is Deeply Misleading

Image taken from the US PIRG website:

UPDATE 4/24/2023: This is making the rounds. I have now seen it on Vice, The Verge , Reddit and I am sure more are to follow. Again, I am sure there were good intentions behind this report but it is very misleading.

I saw this article on PC Gamer by Jorge Jimenez titled “Here’s another e-waste crisis for the e-waste pile: ‘Chrombook churn‘”

I read it and while there are some points to be made, I felt the article was a bit misleading and short sighted. The whole article is based on a report from a consumer advocacy group called the Public Interest Research Group (the US PIRG), so rather than point out shortcomings of Jorge’s article I decided to go to the source and criticize it there. You can find their article written by Lucas Gutterman here:

You can find the US PIRG report also written by Lucas Gutterman here:

What is US PIRG’s mission

“Through research, public education and outreach, we serve as counterweights to the influence of powerful special interests that threaten our health, safety or well-being.”

They focus on right to repair, cutting down ewaste or the overuse of antibiotics amongst other topics.

I am onboard – I think those are all worthwhile causes and applaud their work. Keep it up PIRG!

So what’s wrong?

Well, they got some things wrong in their report and article. They also have some things right and I’ll highlight those as well. I will just go through their claims one by one and address each one. I am addressing these claims as a Director of Technology who manages a fleet of over 300 Chromebooks in a small independent school for the past 5 years.

Claim #1: COVID-19 forced schools to go into distance learning and students needed devices to effectively do their work and Chromebooks were an obvious, affordable option for schools and families around the world.

I don’t think anyone can argue that. In fact they state that in the last quarter of 2020 Chromebook sales were up 287% than in 2019. It’s a weird statistic to throw out in 2023, but maybe that was the latest data they could find. At any rate, it certainly shows the popularity of the device type.

Claim #2: Schools have piles of working Chromebooks that have become e-waste because they’ve expired

What PIRG is talking about here is the Auto Update Policy that applies to Chromebooks. Google will provide 6 years of auto updates for a Chromebook based upon its release date. So if a new Chromebook is released in April of 2023, it should receive updates until April of 2029. You can find an up to date list provided by Google by clicking here:

After the 6 years, the device continues to work, but will not receive newer features or security updates. 6 years is a pretty long time for a device that may only cost the school between $250-$400. That is a good value in my opinion.

Claim #3: Chromebooks take a heavy toll on the environment

PIRG claims that over 31 million Chromebooks sold globally represents 8.9 million tons of CO2e emissions. I have no doubt of their calculations here – I don’t know how this is calculated, but I am not doubting that they would lie about this.

Yep, that sounds pretty terrible, but let’s take a look at how Chromebooks stack up to Windows, Macs and other devices in the USA. What is the Chrome OS marketshare compared to these other devices?

You can find this chart by clicking here:

This is from Statcounter GlobalStats and you can read about them here:

So Chromebooks make up about 8% – what about the Windows or Apple computers that make up over 85% of all computers in the US? Shouldn’t that waste be addressed before Chromebooks? This also doesn’t count Android or iOS devices as well which are discarded at a much higher rate than computers (Chromebook or not)? Here is a stat I found from Statista about smartphone adoption rates:

I would think that the manufacturing of Windows, Apple computers and smartphones/tablets take a much, much larger toll on the environment than that of Chromebooks do. I believe we need to look at the industry as a whole and not just a specific manufacturers or specific types of device.

Claim 4: …only one-third of this electronic waste is properly recycled

Again, I cannot refute this claim or have any reason to doubt it. I can state that this is an issue for the school district (or school) and the community. I’ve never heard of a school or district throw away thousands of devices with lithium-ion batteries, but that doesn’t mean that its never (or doesn’t) happen.

If it does happen the schoolboard, the community or other employees need to bring that issue to light and hold those responsible accountable. This is not a fight for Google, Apple, Microsoft, Dell, Samsung, etc.

Claim 5: Chromebooks have a built-in “death date,” after which software support ends

The term “death date” is extremely misleading. I mentioned this above, all Chromebooks are supported for 6 years (it may be a little longer after looking at their list). When the last update happens, the Chromebook does not turn into a paperweight. It still turns on, it still boots up, people can still log into it, people can still use it.

Lucas Gutterman states in his PIRG report that once they no longer receive updates – they cannot access secure websites.

This is pretty laughable. We use Chromebooks at my school after their “death date” as loaners. These students need to access the following websites on a daily basis – all of which are a secure website:

  • The School Information System (to check grades)
  • Their Gmail
  • Any number of educational websites that require a login (No Red Ink, Desmos, Conjuguemos, etc.)

We have never had a student fail to access any of these websites with our out-of-date loaner. As for the state mandated tests, I guess that could be a possibility, but those tests differ from state to state and I would think that as long as the browser met certain minimum requirements it would work.

Just to test it – I took a Chromebook that is past its “death date” and logged into my retirement account. Yep – no issues. I think they have pretty rigorous security around their website too.

Claim 6: …average expiration date for all devices as four years away

This is the list of the expiration date of when certain Chromebooks will no longer receive updates. All this tells me is that those Chromebooks have been on the market about two years – that’s it. They seem to suggest that most Chromebooks only receive 4 years of updates – this is incorrect as stated earlier.

Claim 7: Manufacturers who make Chromebooks typically do not sell new spare parts or otherwise support repair

While some of the report has some truths or are stretching the truth – this is just outright incorrect. They reference another one of their reports (you can read that here: with very little explanation of what they were evaluating.

I can take any of our Chromebooks and tear it down to its frame in less than an hour. I can replace nearly every part of a Chromebook and common repairs (screens, batteries, trackpads, keyboards, can usually be completed in under 15 minutes.

I can also find any part I want from a number of online vendors that specify in just Chromebook repairs. They are not hard to find, are legit businesses and are usually pleasant to work with (at least in my experience) and there is also Amazon.

Claim 8: The way these laptops are designed frustrate repair and reuse

Again, this is incorrect. We have Chromebooks from Samsung, HP and Dell on our campus. I can take a screen out of an older Samsung and put it in our newest Dell and it works with no issues. I cannot say that about Apple, Windows computers or most tablets or smartphones.

It is true that I cannot take a keyboard off a Dell and place it on a Samsung Chromebook, but we always end up with a few dead Chromebooks. One example was a Chromebook had a faulty logic board and the screen would not power on. The rest of the Chromebook functioned fine and there was no visible damage. We gave the student a spare Chromebook and kept the defective one. It was out of warranty which was great for us, we were able to cannibalize it. We ended up using the screen, the battery, the trackpad, a sister board! All those parts at our finger tips waiting to be used.

Again, we can’t do with our Macs, iPads or other Windows computers on campus. If something goes wrong with one of them we more than not have to send it off for repair. Not our Chromebooks, the only ones we send off for repair are ones that are covered by warranty.

In the report, Lucas points out that the bezels are different on Dell Chromebooks from one year to the next. He is not wrong, but do you know what we do with cracked or broken bezels?

As long as the Chromebook is functioning we don’t do anything. If we have to, we will cannibalize that part or pay the $20-30 to replace it ourself and have that part withing 2-3 business days from a bunch of different vendors. If a cracked bezel doesn’t impact the Chromebook’s functionality, we just leave it until it becomes an issue. In 5 years, it rarely has been an issue.

Claim 9: [Google can] Extend the life of Chrome OS software

This is true – he asks Google to extend it to 10 years, but more and more Chromebooks can run Linux. Why not just go that route? I’m not sure I would feel comfortable handing a student a 10 year old Chromebook. For that matter, I wouldn’t feel comfortable handing a student a 10 year old MacBook to use on a daily basis either. Their performance gets very, very sluggish.

Claim 10: [Google can] Extend the life of the Chromebooks hardware

Google does make a Chromebook or two, but I don’t know any schools that use them. I guess what the author is going for here, is that Google require better hardware for Chromebooks and put some restrictions on the OEMs.

The obvious effect to this will be increase prices of Chromebooks making them less attractive for schools. I’m not sure that is a good trade off, but I could be wrong on that one. I do wish the processors were a little beefier in the Chromebooks we buy, but if we were to pay say $450-600 per Chromebook we could get those, but our Chromebooks do seem to meet our student’s needs for the most part.

Claim 11: We have a massive stuff problem

Damn right we do (that is not a proud “damn right” either). He is 100% correct here and it is not just consumers but schools as well. Every school I work at has stuff they bought but don’t use or need. I am guilty of this, but myself and my school try not to be. It’s a constant process to have only what you need. It is a constant battle and one we are aware of and try to address every year.

Claim 12: The least we can do, if we’re giving every student in the U.S. a laptop, is ensure these devices are durable and repairable—not part of a constant churn

I agree and Chromebooks fit that bill. When we switched over to Chromebooks I was worried about their durability. It’s a plastic body, plastic lid, the device flexes a little at times and students can be rough on them (the picture below is the worst I have encountered).

This is an extreme case and definitely some user abuse was going on here. The thing is, if we replace the screen – this beast will still work.

But for the most part – our Chromebooks last 4+ years with ease. They are dropped, kicked, stepped on squeezed into an overfilled backpack and for they just seem to keep going. Chromebooks are very reliable and we are pretty happy with them.

How we manage our Chromebooks

We plan for all of our computers (not just our Chromebooks) to last four years. Our middle school students (grades 5-8) receive a Chromebook in 5th grade. They keep that same Chromebook until they graduate 8th grade. Then we give the Chromebook to the family and they decide what to do with it.

One thing we should do better is give these families instructions on where to take the Chromebook to recycle it in case they don’t want to use it or are upgrading to a newer device.

For our Chromebooks in carts that reach the 4 year mark (or end of updates) we will add those to our fleet of loaners for students. With our current cycle we should be adding to our loaner fleet every 3-4 years. For those older Chromebooks that will be recycling them with a reputable e-waste company or donate them to organizations that can make use of them.

So what’s the big deal?

Most schools will shrug off these articles and reports. We know what our Chromebooks can and cannot do. The problem is when uninformed people read this report and take it as 100% factually correct (which I think I’ve shown it isn’t). Those people can push schoolboards and administration to look for more “sustainable” options which usually means a more expensive option. That stretches budgets, takes resources away from other sectors in the school or district and really asks the school make more compromises.

Chromebooks are a good technology solution for schools (at least right now). I like the mission of the US PIRG but they didn’t do their homework on this topic and I hope they revisit it after talking to some tech directors and departments at schools and get a better picture of how useful and valuable these devices are to those organizations.

The Homer!

Season 1 – Episode 7 – The Homer!

Tony and Patrick are at it again. Check out their continued conversation about AI in education and its implications along with some newer features for Google Classroom coming on the horizon. Check out the show notes below and as always, please subscribe to us using your favorite podcasting app.

  1. Skype and the new Bing AI
  2. AI update from Tony – round one will fail because it is annoying
    1. Tony’s prediction – AI is great but will fail because it is annoying
  3. ChatGPT terms of service – the same as they were – and impossible to use legally if you are a Google Workspace School
  4. Google and Google Bard in AI
  5. Class sets for Google Classroom
    2. Announced a year ago
    3. Fuzzy details
    4. Stick with Edulastic or similar products

Copyright & AI

Tony and Patrick continue to talk about AI in education and what it means. Check out the talking points below and be sure to subscribe to us on your favorite podcasting app.

  1. Copyright case for a comic book that used AI to generate the art
    2. Liken the images to photographs
  2. Tony is on a Committee 
  3. Headphones 

ChatGPT Prompts are Fake

Free computer code on screen image, public domain CC0 photo.

Ok. This was a bit of clickbait.

ChatGPT prompts are real, just like The Real J. Peterman is real.

These prompts are not for ChatGPT, they are for you, the end user. The prompts do not grant special powers, they simply put you, the user, in the correct state of mind. They are designed to help you, the real J. Peterman, ask better questions.

I will speculate this is needed because of the recent decay in writing culture and communication related to texting, communicating with emojis, auto-correct, and my personal best friend Grammarly.

If you want to use ChatGPT, ask it about itself. The more you know about AI (any AI) the more likely you are to understand how to leverage it for a real-world application.

I have used it extensively to solve some problems, but, within the frame of my expertise. I knew what I wanted, and I wanted to see different examples. The AI does not need to “Act as” as long as the person has clearly articulated questions.

If you want to use AI efficiently, learn to communicate with it directly and be precise with your language.

Here is an example of using a prompt vs not using a prompt:

Act as a Storyteller and write one paragraph about a red cat named pluto who eats plastic.

Once upon a time, in a small town nestled among the rolling hills and fields of green, there was a red cat named Pluto. Pluto was a curious feline who loved to explore and play, but he had a peculiar taste for plastic. Whether it was a plastic bag, a toy, or even a container, Pluto would eagerly munch on it, much to the concern of his owners. Try as they might to keep plastic items out of his reach, Pluto always managed to find a way to satisfy his unusual craving. Despite his strange eating habits, Pluto remained a beloved member of the community, and his antics always brought a smile to people’s faces.

Write a fictional one-paragraph story about a blue cat named mercury who eats paper.

In a distant land, deep in the heart of a dense forest, there lived a blue cat named Mercury. Mercury was a curious creature with a unique appetite – he loved to devour paper. Whether it was a sheet of notebook paper, a crumpled up newspaper, or even a roll of toilet paper, Mercury would eagerly chomp away, leaving a trail of shredded paper in his wake. His owners were perplexed by his unusual craving, but they couldn’t help but admire his determination to satisfy it. One day, as Mercury was wandering through the forest, he stumbled upon an ancient tome, covered in layers of dust and cobwebs. Without hesitation, he began to devour the pages, savoring the flavor and texture of the delicate parchment. Little did he know, the book held secrets beyond his wildest dreams, and as he devoured each page, he was unlocking a mystical power that would change his life forever.

Here is my conversation with the AI about using prompts:

Do you need prompts to write content, or at Prompts for the end-user?

As an AI language model, I can generate content without prompts, but prompts can help to guide the content I generate and make it more relevant to the user’s needs. Prompts can also help me understand the specific topic or context that the user is interested in, which can lead to more accurate and useful responses. So both prompts for me and prompts for the end-user can be helpful in generating content. However, prompts for the end-user are particularly useful when they want to get specific information or ideas on a particular topic.

Can I get the same results without a prompt?

As an AI language model, I can generate content without a prompt, but the results may not be as relevant or specific to your needs. Without a prompt, I will generate responses based on my understanding of language and general knowledge of various topics. However, when you provide a prompt, it helps me to understand the context and specific information you’re looking for, which can lead to more accurate and useful responses.

For example, if you were to ask me “What is the capital of France?”, I could provide a straightforward answer without a prompt: “The capital of France is Paris.” However, if you were to ask me “What are some popular tourist attractions in Paris?” without a prompt, I would not have a clear understanding of what specifically you are looking for, and my response might not be as helpful. In this case, a prompt would help me to better understand the context and generate a more relevant response.

So prompts are really to help humans ask better questions?

Yes, that’s one way to think about it. Prompts can help humans to ask more specific and targeted questions, which in turn can help me, as an AI language model, to generate more accurate and useful responses. By providing a prompt, you are helping me to understand the context of your question and what specific information you are looking for. This allows me to better tailor my response to your needs.

Moreover, prompts can also help humans to explore new ideas, expand their knowledge, and generate creative thoughts. For example, writing prompts can inspire writers to create new stories or explore different themes. Prompts can also help individuals to brainstorm new ideas, solve problems, and think critically about various topics.

As an AI you have the same power without prompts. Correct?

As an AI language model, I can generate content without prompts, but the results may not be as specific or targeted to your needs. When a user provides a prompt, it helps me to understand the context of the question and what specific information or ideas the user is looking for. This allows me to generate more accurate and relevant responses that are tailored to the user’s needs.

Without a prompt, I can still generate content based on my training and knowledge, but it may not be as targeted to the user’s needs. Additionally, prompts can be helpful in guiding my responses towards a specific topic or theme, which can be particularly useful when a user wants to explore a specific idea or area of interest.

Does your training data suggest humans have lost the ability to ask for complete and proper sentences?

No, my training data does not suggest that humans have lost the ability to ask complete and proper sentences. While there may be some variation in how people formulate their questions, most people are capable of asking clear and coherent questions that convey their intended meaning.

However, it is true that some people may struggle with expressing themselves clearly, especially if they are not proficient in the language they are using to communicate. In these cases, prompts can be particularly useful in helping individuals to structure their questions and convey their ideas more effectively.

Overall, while there may be some variation in how people formulate their questions, most people are capable of asking clear and complete questions that can be understood by others. And as an AI language model, my goal is to understand and respond to these questions as accurately and effectively as possible, regardless of their specific form or structure.

End of Line

DALL-E! AI-Generated Art- Who owns the AI art you are making?

I attended an AI talk last week. The presenter was an AWS Engineer (Amazon Webservices). They sit on a few committees and advisory counsels for the current administration in Washington, D.C.

The talk was a high-level view of how the technology works. Towards the end, a person in the audience asked, “Who owns the copyright on images produced by AI art?”

The answer: Not You.

This ownership idea connects to other conversations I have had about the terms of service with ChatGPT and my initial chat with the AI about how it handles data.

This technology needs new laws and structures around it, and those will come with lawsuits and public debate. As of now, it is not ready for children to use in a K-12 environment. It is not ready for confidential information and data handling (unless a paid option includes the ability to label data).

In terms of the art, and I assume audio and other media it creates, it is not ready to be used in a business or academic environment where ownership is required.

Image using the DALL-E! system, and embedding the art on your organization’s website. You do this routinely for 2-3 years. Then, one day, you are notified that the copyright owner is seeking justification for using the content in a commercial setting and would like to license the art.

Maybe you are wondering, how can they do this? How can they tag the art and track it years later? There are numerous ways to do this, but if they have an AI that can create art, they have an AI that can track art using techniques that would be invisible to the end user. If I were working at OpenAI, I would develop a steganographic method to find content in the future. This technique would place content hidden within the content on the image. It could be achieved using ratios and distance, allowing even the smallest thumbnail to be discovered.

That’s just one idea from someone who thought about it for a day. Image a team of people who built an AI.

The general rule for operating a business: don’t break the law

If you work at a school or a bank, reading the terms of service concerning minors, confidential data, and copyright is not an option. If you are determined to push forward, have your organization’s legal team review what you are planning, even webinars about advocating use.

Here is my chat with the OpenAI Chatbot regarding how copyright is currently handled (or not handled):

Are familiar with an AI that can generate Art?
Yes, I am familiar with AI that can generate art. There are a number of different approaches to this, but some of the most popular ones include:

Generative Adversarial Networks (GANs): These are a type of AI that are trained by having two neural networks compete against each other. One network, called the generator, creates images, while the other network, called the discriminator, tries to distinguish between the real and fake images. Over time, the generator gets better and better at creating images that the discriminator can’t distinguish from real ones.

Variational Autoencoders (VAEs): These are a type of AI that are trained to learn the underlying structure of a dataset, such as images of faces. Once the VAE has learned this structure, it can generate new, similar images by sampling from the learned distribution.

Style transfer: This is a type of AI that takes two images — one as the “content” and one as the “style” — and blends them together to create a new image that has the content of one and the style of the other.

There are many other approaches to AI-generated art, but these are some of the most popular.
Are you familiar with Dall-E

Yes, I am familiar with DALL·E! DALL·E is an AI-powered image synthesizer created by OpenAI. It was introduced in January 2021 and quickly gained attention for its ability to generate a wide variety of images from textual descriptions, including many that are fantastical or imaginative in nature. For example, DALL·E can generate images of objects that don’t exist in the real world, such as a hotdog-shaped bicycle or a horse with a flashlight on its head. The images generated by DALL·E are unique and often quite striking, which has led to a lot of interest and excitement in the field of AI art and creativity.
What company, person, or entity holds the copyright for DALL-E! generated art?

The ownership of the copyright for DALL-E-generated art is governed by the terms and conditions set forth by OpenAI, the company that created DALL-E. OpenAI holds the copyright to the DALL-E software, and it is likely that the images generated by the software are also considered to be works created by OpenAI for copyright purposes.

However, it is worth noting that the exact ownership of the copyright for AI-generated art is a complex issue that is still being debated in legal circles. There is no clear consensus on whether AI-generated works are considered to be the product of human authorship and therefore eligible for copyright protection, or whether they are considered to be works created by a machine and therefore not eligible for copyright protection.

In the case of DALL-E, OpenAI may choose to license the use of the images generated by the software to third parties, or it may choose to allow free use of the images with certain conditions. The specific terms and conditions for the use of DALL-E-generated art will depend on the policies and decisions of OpenAI.
Does OpenAI use steganography to track DALL-E! art?

I’m not aware of OpenAI using steganography to track DALL-E-generated art. Steganography is a technique for hiding data within other data, such as embedding a hidden message within an image file. To my knowledge, OpenAI does not use steganography for tracking DALL-E-generated art.

It is possible that OpenAI may use other methods for tracking the use of DALL-E-generated art, such as watermarking the images or tracking usage through digital means, but I don’t have any specific information on the methods used by OpenAI. Ultimately, the method used for tracking the use of DALL-E-generated art will depend on OpenAI’s policies and decisions.
Thank you

You’re welcome! If you have any other questions, feel free to ask.

ChatGPT Talks About Zork

I asked ChatGPT this question multiple times: What is Zork?

You can see the answers are constructed differently each time and not pulled from a single source. 

This is why I believe the content needs to be cited as an anonymous source or interview. The AI does not pull from a traditional structured data set. 


Zork is a text-based adventure game first released in 1977 by Tim Anderson, Marc Blank, Bruce Daniels, and Dave Lebling for mainframe computers. Developed between 1977 and 1979 at MIT, and inspired by Colossal Cave Adventure (1976), it was split into three episodes for personal computers (PCs) by Infocom. In Zork, the player searches for treasure in the abandoned Great Underground Empire, moving between the game’s hundreds of locations and interacting with objects by typing commands in natural language that the game interprets.


  1. Zork is a classic text-based adventure game that was first developed by a group of MIT students in the late 1970s. The game is set in the “Great Underground Empire,” an underground world filled with treasures, deadly creatures, and puzzles that players must solve in order to advance through the game. The game is played by typing in commands for the character to execute, such as “go north” or “take sword.” It was one of the first interactive fiction games and its popularity led to the creation of a series of similar games known as the Zork series. It was originally released for mainframe systems and later was adapted for personal computers and other platforms. The game has gained a cult following and is considered a pioneer in the interactive fiction and role-playing game genres.
  2. Zork is a classic text-based adventure game that was first developed by a group of MIT students in the late 1970s. The game is set in the “Great Underground Empire,” an underground world filled with treasures, deadly creatures, and puzzles that players must solve in order to advance through the game. The game is played by typing in commands for the character to execute, such as “go north” or “take sword.” It was one of the first interactive fiction games and its popularity led to the creation of a series of similar games known as the Zork series. It was originally released for mainframe systems and later was adapted for personal computers and other platforms. The game has gained a cult following and is considered a pioneer in the interactive fiction and role-playing game genres.
  3. Zork is a classic text-based adventure game that was first developed in the late 1970s and early 1980s by a group of programmers at MIT. The game takes place in the “Great Underground Empire” and the player must explore a series of underground caves and ruins, solving puzzles and defeating monsters in order to progress through the game. Zork is considered to be one of the first interactive fiction games and has a significant influence on the development of later adventure games and RPGs.
  4. Zork is a classic text-based adventure game that was first developed by a group of MIT students Tim Anderson, Marc Blank, Bruce Daniels, and Dave Lebling in the late 1970s. Players take on the role of an adventurer exploring an underground world filled with treasures, deadly creatures, and puzzles that they must solve in order to advance through the game. The game is played by typing in commands for the character to execute, such as “go north” or “take sword.” Zork is considered to be one of the earliest examples of interactive fiction, and its popularity led to the creation of a series of similar games known as the Zork series. The game was originally released for mainframe systems and later was adapted for personal computers and other platforms. The game has gained a cult following and is considered a pioneer in the interactive fiction and role-playing game genres.

The AI does not have an attributable source. The AI constructs output based on many types of input, and the input sources are not available to the AI.

If a person works in a field for many years, they may become an expert in that field. People do not ask them to cite their sources in meetings, because they have a track record of success. The AI’s knowledge in many ways is similar. Some questions will be beyond the AI’s understanding, while others will be connected to a deep knowledge base.

Policy creation is in flux around AI attribution, citation, etc. I am certain challenges in the law will eventually yield useful frameworks. Until then, the best route is to pick a standard and be consistent.


Good morning fellow reader. Last week I attended a webinar concerning Chat GPT. There are some good questions from the panelist and (spoiler) at the end of the webinar they ask those questions to Chat GPT. The best part of the webinar are when the panelist talk about all the ways they have explored Chat GPT. Also there is a language arts teacher who talks about its writing style and some good tips on how to recognize an AI written paper. At any rate, enjoy the video below!