Wednesday, February 21, 2024

Reflections on The Digital Divide in Education: The Irony of AI Content Detection (they don’t work)

The photo above comes from a recent post on Medium.com by a colleague who teaches computer science at another campus. In his post, my colleague asked a very good question, but he never answered it, so I asked ChatGPT to answer it instead.

Background

The post has a provocative headline, "The Digital Divide in Education: The Irony of AI Content Detection (they don’t work)," which immediately grabbed my attention for a number of reasons. 

First and foremost is the fact that, in my own experience as an undergraduate writing instructor, AI text detection has worked very well on many occasions, yielding deeper and more rewarding experiences with my students by discussing these tools, student support at our College, ethics, academic integrity, and digital literacy in cases of suspected, potential AI-misuse, helping to cultivate a friendly, more effective student-teacher relationship rather than encourage an antagonistic, policing dynamic through the misuse and misunderstanding of such technology. 

To say that AI detection does not work simply because it does not always work seems off the mark. 100% performance 100% of the time seems a little bit of an unrealistic goal, especially for something so complex and multi-layered, not to mention the variety of tools and techniques available that can easily obfuscate such text (as the article rightly pointed out). Nevertheless, to suggest that AI detection is useless or even harmful because it does not always work and requires some degree of resources seems akin to saying that blood tests are useless because they do not always work and require significant resources that only widen the poverty gap.

Secondly, my view about money and resources spent on education does not see the money spent on schooling as an expense. Rather, I see any money spent on education, especially money spent for the education of students in lower economic brackets, as an investment in those students' economic future. When my students complain about the cost of books, I tell them the same thing. I used to struggle to buy books for my classes too when I was an undergrad. I had to choose between work and school, paying for bills, or paying for books too. 

Believe me, I get it. I understand the poverty gap, having straddled it myself as a first-generation college graduate.

But I assure most students that, if they do what they are supposed to in college and make the most of the opportunities available there, any money spent on books or anything else for college actually becomes an INVESTMENT, not an expense, paid over and again, year after year. That college degree will unlock a world of opportunities previously unavailable to them and make a significant impact for generations to come. It happened to me. It can happen to anyone... but nothing comes for free. That's just the way life works.

Lastly, my approach to these tools is highly informed by the research text-matching software systems, commonly presented as plagiarism detection software, and the need for educator training on the limitations and best uses of such technology, which I have engaged in for over three years. 

Yes, AI detection technology has limitations. All forms of technology have their limitations, but these tools offer some affordances that can help us address the very issued that my coleague appears to be concerned with in his post.

Understanding how to use our tools can ultimately help us become better users and enable us to achieve intended outcomes more effectively, in effect, by understanding how to use the right tool for the right problem.

The Question

In his post, my colleague asked, "How can educators and technologists work together to create a more equitable learning environment where integrity and honesty are upheld?"

The original question was actually a bit longer (e.g. "How can educators and technologists work together to create a more equitable learning environment where integrity and honesty are upheld, not by the depth of one’s pockets, but by the merit of one’s efforts?"), but I felt that the last part of this question included language that was evocative yet biased and ultimately unnecessary since I felt the first part of the question already assumed the second part.

Below is the response I got from ChatGPT:


Collaboration between educators and technologists is crucial to creating a more equitable learning environment that promotes integrity and honesty. Here are some strategies for working together:


1. Define shared goals:

Educators and technologists should collaborate to define common goals for creating an equitable learning environment. This could include fostering academic integrity, ensuring access to technology for all students, and promoting inclusive learning experiences.


2. Develop clear policies:

Work together to establish clear and comprehensive policies on academic integrity, technology use, and online behavior. These policies should be communicated to students, parents, and other stakeholders to ensure everyone is aware of the expectations.


3. Implement technology for integrity:

Technologists can develop and integrate technologies that help maintain academic integrity, such as plagiarism detection tools, secure online testing platforms, and tools to monitor and discourage cheating during online assessments.


4. Provide training and support:

Educators need training on how to effectively use technology to enhance learning while maintaining integrity. Technologists can provide ongoing support and professional development to ensure educators are proficient in utilizing technology tools in a way that aligns with educational goals.


5. Address accessibility issues:

Collaborate to ensure that technology is accessible to all students, regardless of their socio-economic status, abilities, or geographical location. This includes providing devices, internet connectivity, and assistive technologies to those who need them.


6. Promote digital literacy:

Work together to integrate digital literacy education into the curriculum. Educators can teach students how to critically evaluate information online, avoid plagiarism, and use technology responsibly. Technologists can contribute by creating user-friendly interfaces and tools that promote responsible digital behavior.


7. Regular communication and feedback:

Establish open lines of communication between educators and technologists. Regular feedback from educators can help technologists refine and improve technological solutions to better meet the needs of the educational environment.


8. Consider ethical implications:

Educators and technologists should work collaboratively to address ethical concerns related to the use of technology in education. This includes issues such as data privacy, surveillance, and the potential for bias in algorithmic decision-making.


9. Involve stakeholders:

Engage students, parents, and community members in the conversation about creating an equitable learning environment. Solicit feedback and involve them in decision-making processes related to technology use and educational policies.


10. Continuous improvement:

Foster a culture of continuous improvement by regularly assessing the impact of technology on the learning environment. Gather feedback from educators, students, and other stakeholders to identify areas for improvement and make necessary adjustments.


By fostering a collaborative and proactive relationship between educators and technologists, it is possible to create an educational environment that values integrity, embraces technology, and ensures equitable access to learning opportunities for all students.


Discussion


It is interesting to note that a text-generative AI system considers AI-content detection to be part of a larger, more complex strategy, involving several interdependent parts. I'd also like to point out that Points 4 and 6 are areas where educators can most effectively improve both short-term outcomes and long-term outcomes at any educational institution.


As with most things in life, the truth of the matter does not lie at one extreme or another but rather in the middle somewhere. AI and AI-generated content detection are simply too new for us to be making such sweeping statements yet. I mean, they are big, bold, and grab a lot of attention, yes.


Sexy headlines make for lots of clicks, perhaps, but I would caution rather to keep our assumptions in check. Humans are notoriously terrible at predicting the future of their own technology.


Thursday, November 14, 2019

Nano Update #2: Baby Shrimp do-do-do-do-do-do!


Last week I was surprised to discover something new in my nano tank.

At first, I wasn't sure what I was actually seeing. I thought it might be a tiny worm, you know, a planarian or something that fish-keepers commonly find in tanks that are overpopulated or overfed, or maybe just some bit of detritus that had landed on an anubias coffeefolia leaf. Then I noticed it was moving against the current, and I immediately knew what I was looking at: a baby shrimp (aka shrimplet)!

It was so small that it was very hard to see. I mean, neocaridinia shrimp are small enough, even when fully grown, but these micro-mini-shrimp have got to be the smallest babies I have ever seen... and I've bred bettas before (aka Siamese fighting fish), so I know how small some tiny baby fish  can be (I understand that bettas are among the smallest of baby fish), but these shrimplets are ridiculously small! In fact they are so small that I can't get my old iPhone6 to properly focus on them most of the time, as you can tell from the picture below, where one of the shrimplets is resting on a java fern leaf.




To be honest, I only spotted the first shrimplet by chance, really, but then I started looking around the tank and noticed several other baby shrimp. It's hard to say how many are in there exactly, but I counted at least eight this morning, roughly the same size as each other, and all of them starting to get some color.

I seem to have a habit of setting up environments that encourage fish to breed. I don't know. I chalk it up to experience, really. I've been a fish-keeper most of my life at this point, and I "ain't no spring chicken" if you know what I mean..! Even the filter on this nano tank is 30 years old (and running just fine, which is very impressive), so yeah, I've been in this hobby for a while, I guess.

Speaking of that filter, it's a little noisy, so I should probably replace the impeller - another thing I have learned from past experience - but it still works so well that I have it on the lowest setting possible. I suspect that even at its lowest setting it has probably sucked up a few shrimplets, despite the foam pre-filter over the intake tube, but if that's the case, these guys are the survivors and probably too big to get in any major anymore. They are certainly growing, and judging from their coloration and activity level, they seem to be thriving.

So what do I do now? The answer is simple. Continue with the status quo. In other words, keep doing what I've been doing all this time. In general, if the conditions are right for breeding, they are right for growing the babies out. Therefore, I continue my routine and make small weekly water changes, but I am wise enough to avoid making any major changes while the babies are growing. I only clean the algae that builds up on the front glass, just to be able to see inside better and enjoy my tank. I'm not getting rid of any algae on the rocks and plants, however. I keep it there to provide food for the shrimplets.

Anyway, here is the best close-up I could get of one of the largest shrimplets (probably a female, given her growth and the fact that female neocaridinia shrimp are larger than males. I can't see any details on the shrimplets with this camera, but I already have a new iPhone XR waiting to be activated, so I expect to have much better pictures the next time I post.


Keep those elbows wet!


Friday, September 6, 2019

Nano Update 1: Bloody Mary Shrimp


It's been two months since I set up the nano in my office, and nothing has died yet.

That's always a good sign.

I'm glad I waited all this time to finally add some shrimp. It helped me make sure that I knew what I wanted and could find a good deal on what I wanted. I knew I was going to be out of the office all that time, so it was not a good idea to introduce any live animals to the tank anyway.

Instead, I just dropped in a couple of times during my vacation, just to make partial water changes and top off the tank. The plants suffered a bit when the water level dropped after the first three weeks, but I was surprised to see they all survived with just a 15 watt incandescent bulb over the next several weeks. I even got some algae to deal with! Go figure...

I really have to get some better lighting soon, as can be seen from the leggy growth (the distance from one leaf node to another) on the staurogyne repens in the foreground, but to their credit, they are alive too! They aren't thriving, but they are definitely surviving even without strong lighting, which I expected form the other plants but not really from staurogyne repens. I trimmed the dead anubias leaves when I got back from summer vacation but left a little debris for the shrimp that I knew I would soon be buying.

I received them a couple nights ago and brought them to my office the next morning, acclimated them, and transferred them to the tank using a net (to avoid contamination from their water). All seven shrimp survived the trip and seem to have settled in nicely now, grazing on the plant leaves and the little bits of debris that have collected on the sponge that covers the filter inlet tube.

They looked so nice when I came in this morning and saw the tank, that I felt inspired to make a little video of them as an update. Enjoy the scape, listen to some dope beats, and relax.

Thanks for stopping by!

Peace!

Monday, June 17, 2019

Nano Nano!



A couple months ago, a small octagonal tank mysteriously appeared in my garage, and I decided to do something about it.

Having kept fish, plants, and all manner of tanks for many years now, people tend to offer me their tanks and equipment after a while when they've lost interest in fish-keeping. Most of the time I get what I consider to be beginner-type equipment such as colored gravel and plastic plants. I don't want to act snobbish about it because most of us start out with that type of stuff, but sometimes I get lucky and get something cool like an industrial chiller that a colleague gave me one time. I haven't used it yet, but that's something I consider to be pretty cool (no pun intended) if I ever intend to keep some sort of cold-water species. No need for it now, but you never know..!

In any case, I was immediately attracted to the little 5-gallon as a potential hospital tank (this helps keep medication costs down if fish ever get sick) but quickly realized that I could throw some of my cuttings in there and create a pretty nice little nano tank for my office at work. I had a spare HOB power filter (a 30-year old little workhorse, once known as an Aquaclear Mini but now they are called the Aquaclear 20) set up and running anyway, so ultimately, that's what I decided to do. I washed it out and gave it a new home in my office at work.

For hardscape, I went with some nice grey seiryu stone to match the grey walls and furniture of my office. I figured it would blend into the environment and help the plants pop more. I found a vendor on Amazon with some good prices (and good reviews), so I took a chance buying 17 lbs of the stuff for $30. It seemed like a better deal than my LFS, and the reviews were pretty impressive. Man, was I glad I went for it! The rocks were beautiful! I thought I was going to have a couple of pieces left over, but it turned out to be just the right amount and in the perfect sizes for this tank.

Here is a picture of the tank when I first put in the rocks, just to get an idea of the layout.

This was the final hardscape layout I settled on. Let me know what you think!

A couple days later, I brought some cuttings from the plants in my 90-gallon. I didn't disinfect them, so I know that this is going to introduce some snails and probably some pathogens too, but I don't plan to stock this with anything for a few months, so there will not be much for them to survive upon and they will probably die off naturally. I'm not too worried.

I later ordered a small bag of extremely expensive substrate. I've never really used any fancy aquascaping substrate. I went with pea gravel from the gardening section of Walmart when I set up  my 90-gallon many years ago, and I'm pretty happy with it, but I wanted to try something new, so I went with this cool, aquasoil. The 1-liter bag set me back about $10, which was remarkable for such a small amount, but it was just about enough.

Here is the final result! I placed my travel mug next to it to give you some sense of the scale. I think it looks pretty good.


This next picture is what it looks like when I first step into my office in the morning. I think it's pretty cool. My students and colleagues seem to like it too. What do you think?


I know I want to put some Cherry Shrimp or Bloody Mary Shrimp in there, maybe some other type that won't interbreed with them. I also want snails. I'm a little more apprehensive about fish though. It's not a very big tank, so not many fish would be happy there, despite the more than adequate filtration and circulation, plus it's not very warm. That limits me somewhat. I love bettas, and this would make a nice betta tank, but I want to keep shrimp, so a betta is out of the question. I've never kept gouramis but a dwarf gourami might work but I'm thinking even smaller, like maybe endlers or some other small livebearer. I already have 43 neons at home, so no neons. I want to try something different.

Let me know what you think in the comments below! Till next time! Keep those elbows wet!

Sunday, March 10, 2019

90-Gallon Update & Ideas for 2019

90-gallon Update

My last post was way back in May of last year, and a lot (of really good stuff) has gone on in my personal life since then, including my tremendous wedding and an incredible two weeks in Italy and France. It has truly been a roller coaster of the most incredible kind this past year or so.

Needless to say, however, my tank has borne the brunt of my negligence. I had some pictures of the tank back in mid- July that I never posted, so I think I'll start with those pictures first, a sort of then and now...

First, lets look at the tank on July 14 last year. I picked three pictures that show slightly different aspects of the tank, so I will start with the one that focuses a little more on the lush carpet of staurogyne repens along the foreground.

If you're wondering what the little blue box is, by the way, it is an enclosure where I deposit the babies as I find them, to keep them from getting sucked into the filtration system.


It took a lot of work to get that lush carpet of staurogyne repens you see here, and there is more to the tale of this staurogyne repens that I will detail in a future post. If you look carefully, however, you can see that I was already letting things go. There are some strands of algae on top of the vals.

That repens looks lush here too, but it badly needed a little trim too, and boy did it get one this past weekend! I only hope it's not too late. I'm pretty confident they'll be fine. We'll see.


I really love the broad, bright green leaves of these Amazon swords. They grew even more lush soon after this picture was taken. Believe it or not, I have kept this particular line for about twelve years, and I have brought them bac from the brink on more than one occasion.

Speaking of bringing them back form the brink, about 20 baby ancistrus (aka bristlenose plecos) got out of the blue plastic and mesh breeding container you see in the top right side. Somehow, the separator fell to the bottom of the tank instead of staying at the top. The suction cups went bad or something, but either way, the baby ancistrus all escaped into the tank, and when I neglected to feed them - I decided to let them go hungry for a while because their waste was throwing off the water chemistry too much - they started in on the Amazon swords. You'll see some of that damage later.


Ancistrus  have another downside: They are known to poop - a lot - and having over 25 or so in a 90-gallon tank is never going to be a good idea unless you are making regular large water changes. I'm paying the price for my negligence though, believe me!

7 months later...

I stopped taking care of the tank as much, and I have paid the price. I should have taken pictures before I started cleaning up, but I thought of it too late. Now let's take a look at what's left after cleaning things up a little, following seven months of neglect.


Looking at it now, it doesn't seem so bad. I mostly see just a lot of yellowing of the leaves, which was to be expected. After all, I hadn't added any liquid fertilizer in about six months and had only topped off the tank from time to time instead of doing regular water changes. That's also what saved it from being drowned in algae. I had also trimmed much of the damaged parts of the jungle vals, which were looking rather shredded before, so the picture really does not do the damage justice. However, the following picture shows a closeup some of the damaged leaves of the sword plants. 


Here's one of the (cute!)little bastards below, probably taking a break from munching on my swords.



Though you can't see it well in these pictures, I trimmed most of the staurogyne repens really hard, as evidenced  by the cropped bare stems int he pictures below. The staurogyne in the picture above, however, was spared for a week. I just got tired of trimming and replanting.

I'm working with 48 linear inches of staurogyne for a carpet. It can take hours to trim and replant.

The bottom of their stems had gone bare from being drowned out by the leaves above them, but now that they are exposed to light, and I'm hitting the tank with ferts again, I fully expect them to bounce right back.

Believe it or not, I've seen worse, like when a strange disease (a least it seemed like a disease) melted the repens to the point that I thought I was going to to lose it all, only to see it come back in less than a month.

Here are a couple pictures of the tank a week later (March 2). You can see that the plants are starting to recover and their colors are getting stronger.




Anyway, it's time to post this long-awaited and highly unanticipated update... finally! 😃 We'll take a look at the fish room next time. I promise. I've got some updates on that too, coming soon...

Keep those elbows wet! 


Sunday, May 20, 2018

90 Gallon Update: The Heady Days of CO2


90-gallon Update

The Heady Days of CO2 

After just 21 days since my last post, I can already see a great deal of new growth in the 90-gallon tank. I've had to trim the valisneria at the waterline to keep it from blocking the light over the alternathera reinicki mini, the red plants on the left side of the tank. What's worse, the vals were developing those long strings of algae at the top of those long, beautiful strappy leaves, and I was not surprised, given the fact that they were as close to the lights as any plan can get. I had to resolve that algae issue as soon as possible. I know how hard it can be to get rid of that air alga once it gets established, so I'm always looking out for new strands to remove them as soon (and cleanly) as possible. Any little piece that breaks off can start a new strand, so I have to go slow and carefully each time. Trimming the leaves just seemed to be a more effective way of getting rid of both issues in one fell swoop.

I cut back a couple of leave at the water line first, just to test it. I wanted to see if the leaf would die and melt away. If so, I wanted to see how that affected the plant. To be honest, I don't see that it hurt much at all. In fact, it might be the reason why those vals are threatening to overrun the tank! It definitely made removal of that hair algae much easier.


It's pretty clear that the vals are booming. They are sending out runners everywhere, and growing by the day. I'm definitely going to have to remove several of them soon before they overgrow the tank.


The little blue basket up in the top right corner of the tank is where I am holding about 20 baby ancistrus.  I intend to move them over to the mini-fish room in the garage to grow out, but I'm somewhat hesitant because I had so many die that way last time (I know at least one of those babies survived, but it looks like it was probably only that one because I haven't seen any others in a really long time). I treated that tank with meds and water changes a few weeks ago, and everything has been fine for a long time, but I'm still a bit wary. I want them to get a little bit larger before I move them.


Speaking of ancistrus, here is one of the larger ones in the 90-gallong tank. I wanted to demonstrate with this picture how much the stringy little alternanthera reinicki mini has grown and how strong it has become (check my last post), given a steady supply of CO2 and smaller, regular doses of ferts.


Since it kind of fits with the whole theme of aquatic plants and nature too, I decided to share a picture below of my youngest son on a recent class field trip to Billie Swamp Safari on the edges of the Florida Everglades. Alligators are "kind of our thing" down here in South Florida...


Sunday, April 29, 2018

Let's Get Planted!

Planted Tank Tips 

After lightly dosing the planted tank I keep in my living room with trace nutrients earlier today, it occurred to me that I could share a few bits of wisdom that I've gleaned over the last couple years of keeping a planted tank. I have to offer a disclaimer, however, that I am not an expert on this topic by any measure of the word. Instead, I approach this topic as little more than a hobbyist who has had his share of successes and failures with planted tanks over the years.





























Here are some tips (in no particular order)...

  1. Lighting and Plant Selection: Go with low light plants if you don't have good lights. Start with the easy ones like anubias and java fern (or java moss if so inclined), moving up to amazon swords and others before you go with more difficult plants. Watch a few YouTube videos and read a few online forums to familiarize yourself with the needs of the plant. Then try not to mess with the plant too much after you set it in the tank. Give them time to adapt. Patience is essential in the early stages.
  2. Lighting: Get decent lights. They don't need to be any particular top brand, or any name brand at all. Just get as much coverage and as bright a light as you can. I have had success with relatively "low-cost" LED light strips (the white/blue type, not the flexible strips) that I bought on eBay, but I still spent about $100 on lights for my main tank all told, just to have enough coverage. I have also had a great deal of success with LED floodlights (similar to these) in my fish room.

    Tip: If you're going with floodlights, look for something in the daylight color range (6000K).
  3. CO2: CO2 definitely helps. The level of CO2 in your tank will limit your plant growth. You can go with the liquid form at first if you're not sure about the relatively steep cost of starting up a CO2 system, but if you stick with it, you will eventually want to get a tank, regulator, diffuser, and CO2 airline. Don't worry. It's worth it.

    In an aquatic environment, CO2 is not as abundantly available as in the air we breathe. Increasing the level of CO2 in your aquarium will make your plants grow faster and better. This is the fuel for their cell-building. More fuel means more more cell-building. Isn't that the point? As an added bonus, CO2 helps control algae as well!

    Tip: Keep the dosing of CO2 constant as well. Fluctuating CO2 levels can be problematic.
  4. Fertilization and Algae Control: When using liquid nutrients, spread the dose across the days of the week. For example, if your total dose of a given nutrient is 9 capfuls once per week, administer it as 3 capfuls, 3 times a week instead. A plant can only consume so much at any given time. Once it hits the maximum rate of absorption, the rest of the nutrients are left floating in the water column, ready for any algae that might be lurking in your tank. Plants are able to uptake nutrients much more easily when the dose is spread out, and it leaves fewer nutrients for algae to consume in the end.

    NOTE: This is definitely a balancing act with any waste that you might have coming from fish, invertebrates, or other life in the tank too, including the remains of dead, wilted leaves which decompose and add more nitrites to the system. Dead leaves are inevitable, and fish waste is a natural source of nutrition for an aquatic plant, but it can get out of hand very quickly, especially if you have a large die-off of plants, an over-stocked tank, or too much food waste.