Using AI?

[Reefing_addiction]

@Johnd651 the problem lies in what information AI can actually analyze…which only includes index sites. It can’t determine what’s fake news and real news….even paid ChatGPT can’t get chemistry stuff right ….yup I’ve paid for it and used it and it was sadly still wrong

 

[mrhammy]

I just gave chat GPT4 a shot at:

I want to build a fish stocking list for a reef aquarium, 120 gal tank 4ft x2ft x 2ft. I will have corals and would like peaceful fish, a few tangs would be nice. What fish should i get and what order should I add them

It returned:

Building a fish stocking list for a 120-gallon reef aquarium involves selecting fish that are not only beautiful and peaceful but also compatible with corals and each other. Here is a suggested fish list and the recommended order for adding them to your tank:

1. Clownfish (Ocellaris or Percula Clownfish)
   
   • These are hardy, peaceful, and charming fish that are a staple in many reef tanks.
   • Add these fish first as they are generally robust and easy to care for.
2. Royal Gramma or Orchid Dottyback
   
   • A colorful addition with a peaceful nature.
   • They are relatively easy to care for and can be added early on.
3. Blennies (such as the Tailspot Blenny or Lawnmower Blenny)
   
   • Blennies are peaceful, have lots of character, and help control algae.
   • Add these after your clownfish and dottybacks to provide them with a stable environment.
4. Gobies (e.g., Yellow Watchman Goby)
   
   • Gobies are peaceful and can form symbiotic relationships with pistol shrimp.
   • They can be introduced after the blennies.
5. Tangs (such as the Yellow Tang or Kole Tang)
   
   • Tangs are active swimmers and need space, but they can coexist peacefully in a large tank.
   • They should be added after the smaller, less aggressive fish have established territories.
6. Flame Angel (or similar dwarf angelfish)
   
   • While often reef-safe, some may nip at coral, so monitor their behavior.
   • They should be one of the last fish to be added to ensure a stable environment.
7. Wrasses (e.g., Six-Line Wrasse or Fairy Wrasse)
   
   • These fish are colorful and generally peaceful.
   • Introduce them later in the stocking process due to their semi-aggressive nature.
8. Anthias (e.g., Lyretail Anthias)
   
   • They add vibrant colors and movement to the tank.
   • Add them after the wrasses or concurrently, keeping their social structure in mind.

Tips for Successful Stocking​

• Quarantine each new fish before adding them to the main tank to prevent introducing diseases.
• Ensure your tank's filtration and water parameters are stable and adequate to support the bioload.
• Monitor fish behavior closely after each addition to ensure compatibility and adjust as necessary.
• Consider the feeding needs of each species, as some may require specialized diets.

By introducing fish gradually, you allow your tank to adjust and maintain balance, providing a healthy environment for all its inhabitants.

 

[Johnd651]

@Johnd651 the problem lies in what information AI can actually analyze…which only includes index sites. It can’t determine what’s fake news and real news….even paid ChatGPT can’t get chemistry stuff right ….yup I’ve paid for it and used it and it was sadly still wrong

See, that doesn't worry/ bother me. It's the fact that it's "learning ". At first it's indexed sites with no knowledge... but it is learning what is correct which has been proven with some crazy examples and then using that forward to index additional supporting info, that's kinda neat but scary.

 

[ElementReefer]

It’s smart, but it’s definitely not perfect. I use Claude 3.5 Sonnet. I do not rely on it for chemistry calculations, it often hallucinates products and parameter ranges, and when trying to do conversions. But it is helpful for tank chemistry and biology as a general topic.

It’s great for coming up with ideas, helping you organize your thoughts, and strangely it seems to be more reliable and focused when you tell it that a situation is urgent.

 

[iReefer12]

I wonder if AI could be used to write code for Apex, could there be more to unlock.. not sure what… maybe seasonal table settings, maybe Vortech profile & schedules, Radion/Sky profiles & schedules.. that mimic real world but adapted for the size of tank you have…

I’ve used chatGPT to write a few clauses for a work document, it was excellent, gave me a starting point and a few adjustments to make it my own and it was perfect.

 

[Red_Beard]

I use it to help write computer code. You have to still know what younare doing to ask the right questions and debug its output, but it gets you about 90% there and saves a ton of time. In my experience what you get is largely dependent on the question you ask, depth, quality, scope. The more concise you ask a very directed question, the better your answer will be.

That said, it is just a large language learning model, that has been trained with crap scraped from the anals and sewage lines of the internet as well as authoritative sources, so you have to take all output with a grain of salt, same as in this forum type setting.

 

[Johnd651]

I wonder if AI could be used to write code for Apex, could there be more to unlock.. not sure what… maybe seasonal table settings, maybe Vortech profile & schedules, Radion/Sky profiles & schedules.. that mimic real world but adapted for the size of tank you have…

I’ve used chatGPT to write a few clauses for a work document, it was excellent, gave me a starting point and a few adjustments to make it my own and it was perfect.

I've used it to write python scripts... better then what I was thinking

 

[littlefoxx]

 

[Subsea]

In my personal experience, every time someone has asked for an AI about something that I have some level of expertise in, it's basically a garbage output. I have seen this for electronics, for music theory, and reef keeping. AI is very good at fooling people who don't know any information. I was arguing this with someone who was very adamant about AI. He claimed that he had ChatGPT write legal filings for his child custody battle. Needless to say, IMO if his wife gets full custody, maybe ChatGPT will have been worth something.

Kudos to your discernment.

 

[Dr. D]

Anyone interested in the development of AI should read Clayton Christiansen’s The Innovator’s Dilemma (1997), where he discusses the phenomenon of disruptive innovation— a term many people think they understand, but don’t.

To simplify a great deal, what it means is that successful new technologies often begin as less effective than current technologies— but if they’re cheaper and/or more easily available, they will tend to crowd out the old tech anyway, sometimes catching up in quality, sometimes not. He cites many examples, particularly in the area of disk drives, etc.

A very basic example: the first printed books weren’t objectively better than old books copied by scribes— manuscripts handwritten by monks were often gorgeous, much “better” than the ugly, smudged things that first came off Gutenberg’s press. The small proportion of the population who could already read scoffed at this new innovation, which they didn’t need. But the printing press brought written words to the masses, giving them new content and reasons to learn how to read. Eventually printed books took over, and printing improved. These new books were “good enough” for most people, and they widened the market for books and information. (Later on, in a smaller example, paperback books were objectively of lower quality than hardcovers… but they made books more accessible to more people at lower price points, and they now vastly outsell HCs, to the chagrin of some book lovers. Today, websites and YouTube are taking over the functions of many books, to the chagrin of many. I’ve watched hundreds of hours of YT on reefing, but purchased no books.)

This concept of “good enough” is the key to understanding disruptive innovation. I think we’re fast approaching the point when AI will be “good enough’” for many more applications than we see now. Yes, now it’s often laughable. AI can, strangely, hallucinate, and seem to lie. We’re still better at almost everything than AI is. But AI will be deployed on more and more tasks, first where the stakes are low. It will improve faster than anything has ever improved. Eventually we may refuse to allow a human doctor to operate on us, since AI will be vastly more experienced. (I’m sure there will always be a human around, like the vestigial driver in some self-driving trucks.)

So yes, I do envision a day, perhaps not very far away, when a particular AI (not necessarily any AI) will be the definitive source for reefing questions, just as another will specialize in brain surgery. I think AI will be fragmented like this, into niches, hopefully avoiding the centralized Overmind/doomsday/Skynet scenario imagined by so many SF films (Terminator, Matrix, Dune….) For now we can laugh at it, and rightly so. Soon we won’t be laughing.

The genie can’t be put back into the bottle, but I do worry about a full-on Luddite rebellion as jobs start to require technical skills that most people won’t be interested in learning.

And now back to your regularly-scheduled Christmas programming.

 

[Reefing_addiction]

Asked AI to generate a photo. I used both the scientific names and the common names of tangs.
“Santa in his sleigh that is a reef tank aquarium being pulled by a gem tang fish, orange shoulder tang fish, blond naso tang fish , achilles tang fish, Acanthurus olivaceus, Tomini tang fish, sohal tang fish , purple tang fish, and a chevron tang fish”

“Santa in his sleigh being pulled by a Zebrasoma gemmatum, Acanthurus tennenti, Naso vlamingii, Acanthurus achilles, Acanthurus olivaceus, Paracanthurus hepatus, Acanthurus sohal, Zebrasoma xanthurum, and a Ctenochaetus hawaiiensis. Each one should have antlers. The sleigh should be a saltwater aquarium with fish.”

Since I didn’t get what I want I fixed it