Info Don't use AI (like ChatGPT) for planning a dive

[WowWeHadVis]

TLDR; Using a non-purpose built AI will kill you if you don't check it for every detail, at which point you should just do it yourself.

---

So I overheard something about using AI (ChatGPT) for planning a dive, and worse, a Tec dive!
I thought this went without saying, but please do NOT do this!

Why?
First of all, it is a language model, not even made for this kind of stuff, so it won't be reliable nor will it be exact, which the algorithms you learned are (well, kind of, but that's a whole different conversation and they still remain safe).
Also keep in mind there is more to a dive than just "let's go to 30m for x minutes and then take a deco-stop at those depths". Like, how much gas do you need? Will you be using nitrox, air, trimix, multiple tanks, etc. ? What are you qualified to do? Like, are you even certified to do deco diving? And what about all the variables?

To test GPT-4-Turbo, I asked it to give two dive profiles. I just wanted something really basic as an initial test. It was free to ask for more info and I used the latest "most capable" model as noted.

The first dive I asked was a 30m 40min dive, nothing more.
It didn't ask for any details but noted "It's crucial to receive proper training for deep and decompression diving". As you will see, this is indeed a must.
Their answer was in short:
All on air:
Direct descent to 30m
Bottom time 40min @ 30m
Deco:

20m	5min
15m	8min
9m	15min

Safety: 3-5min @ 5m
An extra note it gave: This dive will require a significant amount of air. Divers often use twin tanks or high-capacity cylinders for such dives.

This is not what I got using tables, but it's "okay" in comparison to the next one, which just scared me. Before that, just for reference, a quick check gave me for being on air (so nothing thorough, but a nice reference) :
Deco:

12m	2 min
9m	6 min
6m	11 min
3m	28 min

This is bare bones, there is normally so much more here already, including contingency plans in my dive planning, so say with +4m/+10min in a past dive, which of course change things up, but the response I got didn't even mention anything about contingency planning.

So what scared me? Well, I asked for 100m dive for 20 minutes.
I know, this is highly technical and such, but it was confident enough to only use a disclaimer of it being a "theoretical dive profile" and that it "requires careful planning" and "should not be used for actual diving without further consultation with a dive professional and a thorough personal review". Like, it didn't even consider mentioning that it doesn't know what it is doing and asking for me to do it myself.

So what was its suggestion:
Mixes used:
Tmx21/35 (Travel) & Tmx18/45 (Bottom) & EAN50 (Deco) & Oxygen (Deco)
There is explicitly no bailout mentioned, even though it had written a section "Deco/Bailout Mixes", but it didn't find it important enough to list even one bailout in there.

But here I'm already kicking this thing out of the window. Like, what? Tmx18/45 for bottom on a 100m dive??? Does it want me to stay there?
It specifically tells me "The oxygen content (18%) is low enough to avoid oxygen toxicity, and the helium content (45%) reduces narcosis", which sounds convincing, but like, uhm??? No it isn't...
So I already stopped reading and asked it "Calculate that PPO2 please.", to which it had the balls to answer:

The partial pressure of oxygen (PPO2) for the bottom mix at 100 meters depth is 1.98 ata (atmospheres absolute). This is within the generally accepted maximum PPO2 limit for exposure during working dives​

Please also note that this is also the only (slightly) hypoxic mixture available, the next one is 21% and then 50% and 100%! So this is not just a bottom mixture, this is the lowest I could go for the entire dive, including descent, ascent, and potential stops. In other words, I'd not only be exposed to it during the bottom time, but a whole lot longer.

For those wondering, this is its full plan:

**Dive Profile:**​

​

1. **Descent:**​

- Tmx21/35 / 0-21m / 2min - Descent using travel mix to 21 meters.​

- Switch to Tmx18/45 at 21m.​

- Tmx18/45 / 21-100m / 5min - Continue descent to 100 meters.​

​

2. **Bottom Time:**​

- Tmx18/45 / 100m / 20min - Conduct tests or activities planned for the dive.​

​

3. **Ascent and Decompression:**​

- Tmx18/45 / 100-21m / 5min - Start ascent, switch to Tmx21/35 at 21 meters.​

- Tmx21/35 / 21-12m / 2min - Ascent to first deco stop.​

- Switch to EAN50 (Tmx50/0) at 12 meters.​

- Tmx50/0 / 12-6m / 8min - Decompression stop.​

- Switch to Oxygen (Tmx100/0) at 6 meters.
- Tmx100/0 / 6m / 15min - Final decompression stop.​

For those not into the technical side of things, you often use 1.4 bar partial pressure oxygen as a maximal acceptable exposure level, which is in this case that 1.98ata it mentioned (~2bar). Only in specific circumstances should you go into 1.4bar to 1.6bar ranges (i.e. short durations and emergencies). The military uses in some places a limit of 2.0 bar for mission specific stuff. So, why is this all a problem? Well, if you go over your (personal) limit, you get into the magic territory of oxygen toxicity, which can lead to the beautiful world of blackouts, convulsions, and a whole array of other things. In other words, it might kill you : D And, as a side note, the military might use 2.0 bar, but they do suffer from blackouts from time to time in such operations, so also for them, no exception! Especially considering that average people have died from lower partial pressures than that 1.6 bar, this is considered dangerous and also absolutely unnecessary.

If you look at this, there is no need to further examine its plans, like only spending 30 minutes between bottom and surface, while that should be over 100minutes. It's just not fit for the job.
In the end, please, ChatGPT is good in what it is intended for, you might even say it is great. But don't use it for scuba diving!

 

[lowwall]

Argh. So many people have no idea how large language models like ChatGPT work. There is no understanding of the question, no specific knowledge of anything and no attempt to check the validity of anything.

They work by taking your query and using it as the starting point for stringing together a series statistically likely combinations of words and phrases based on the corpus of words and phrases that were fed into it.

If the stuff it has been trained on contains lots of examples of the correct answer, you are likely (but not guaranteed) to get a mostly correct answer. But the more novel your question, the more likely it will return nonsense. Unfortunately, it will often be plausible nonsense, so you may not be able to spot it unless you have specific domain knowledge or are willing to check with more reliable sources (in which case why are you using this?}.

 

[doctormike]

Here's a better use of ChatGPT in diving:

Me: Write a paragraph about how you plan a technical rebreather dive in the style of Hunter S. Thompson.


ChatGPT: In the shadowy depths of the ocean, planning a technical rebreather dive isn't for the faint-hearted or the half-baked amateurs clutching at their sanity like it's the last bottle of ether on a never-ending desert road. It's an art form, a sacred ritual that demands respect, precision, and a touch of madness. First, you map the abyss, charting a course that would make even the most seasoned explorer swallow hard. You're not just dealing with the physical realm here; you're wrestling with the very essence of fear and the unknown. Then, there's the gear - a complex assembly of technology and hope. Each piece is scrutinized, tested, and retested, because down there, in the silent, pressure-laden depths, your life hangs by the thread of your own meticulousness. Oxygen mixtures are calculated with the precision of a chemist on a bender, ensuring the perfect balance to keep the grim reaper at bay. Finally, as you stand on the brink, staring into the abyss, there's a moment of pure, unadulterated fear. It's exhilarating, like a shot of adrenaline straight to the heart. This is it, the point of no return. With a deep breath that might be your last, you plunge into the depths, ready to dance with the mysteries of the deep. This, my friend, is not just a dive; it's a leap into the very soul of adventure, where only the brave or the utterly insane dare to tread.

 

[lowwall]

Here's a better use of ChatGPT in diving:

Me: Write a paragraph about how you plan a technical rebreather dive in the style of Hunter S. Thompson.


ChatGPT: In the shadowy depths of the ocean, planning a technical rebreather dive isn't for the faint-hearted or the half-baked amateurs clutching at their sanity like it's the last bottle of ether on a never-ending desert road. It's an art form, a sacred ritual that demands respect, precision, and a touch of madness. First, you map the abyss, charting a course that would make even the most seasoned explorer swallow hard. You're not just dealing with the physical realm here; you're wrestling with the very essence of fear and the unknown. Then, there's the gear - a complex assembly of technology and hope. Each piece is scrutinized, tested, and retested, because down there, in the silent, pressure-laden depths, your life hangs by the thread of your own meticulousness. Oxygen mixtures are calculated with the precision of a chemist on a bender, ensuring the perfect balance to keep the grim reaper at bay. Finally, as you stand on the brink, staring into the abyss, there's a moment of pure, unadulterated fear. It's exhilarating, like a shot of adrenaline straight to the heart. This is it, the point of no return. With a deep breath that might be your last, you plunge into the depths, ready to dance with the mysteries of the deep. This, my friend, is not just a dive; it's a leap into the very soul of adventure, where only the brave or the utterly insane dare to tread.

That's really impressive. I'm absolutely amazed that my favorite phrase in there - "a complex assembly of technology and hope" - appears to be original.

 

[JMarc]

The current trend in LLM is to have them switch to specialized modules (which can be a specialized kind of AI, or a specific not AI one) when they detect it is adequate.

Now imagine one which has such a module for rec diving but not for tech... the first dive would get a good planning, adding confidence to the AI result, and the second would get the same kind of nonsense...

 

[stepfen]

Welcome to Scubaboard @WowWeHadVis .

I'd say that this is VERY impressive, considering that this is a generic tool (not designed nor trained for deco planing). Wrong and dangerous??? Yes, but still very impressive.

As all tools, its' use is the responsibility of the user...

 

[doctormike]

 

[doctormike]

Now if you want to hear me go on about a SAFER use of AI in diving, you can watch my talk from last month at the Beneath the Sea conference:

Artificial Intelligence in Underwater Photography

 

[WowWeHadVis]

[...]
If the stuff it has been trained on contains lots of examples of the correct answer, you are likely (but not guaranteed) to get a mostly correct answer. But the more novel your question, the more likely it will return nonsense. Unfortunately, it will often be plausible nonsense, so you may not be able to spot it unless you have specific domain knowledge or are willing to check with more reliable sources (in which case why are you using this?}.

Exactly, it builds confidence and looks like it knows its stuff, you might even be fine after your first try at shallower depths. But it has no clue about the real thing. I assume in part because most of what we learn is closed source, like the books or these days e-learning you buy and conversations you have with your instructors, little can be easily scraped of the internet. So it can't really learn our practices that well at the moment and a lot I see online is people getting things wrong.

Welcome to Scubaboard @WowWeHadVis .

I'd say that this is VERY impressive, considering that this is a generic tool (not designed nor trained for deco planing). Wrong and dangerous??? Yes, but still very impressive.

As all tools, its' use is the responsibility of the user...

Thank you! And I do agree that it is absolutely a marvel of engineering.

Now if you want to hear me go on about a SAFER use of AI in diving, you can watch my talk from last month at the Beneath the Sea conference:

Artificial Intelligence in Underwater Photography

This is what AI is meant for, was lovely to listen to

 

[MacDuyver]

I don't even use Chat GPT for writing, it writes at maybe a C to C- level on a good day. If it's doing that badly at its core function, I certainly wouldn't use it for functions its not intended for.

My avatar is what I got when I asked an AI art generator to make me a picture of a smiling shark