Uh. Wow! ChatGPT

[JamesCaruso]

“If students could lean on ChatGPT to pass their MBA final exam at one of the top business schools in the country, what will that mean for the next crop of founders, CEOs, and working professionals?”

https://www.inc.com/sarah-lynch-/chatgpt-just-passed-an-mba-exam-how-will-it-change-business.html

 

[James K]

I think it's no longer a question of if AI can do this, but should AI do this. It's more of an ethical issue at this point, and I'm not sure how I feel about it.

I think its not even a question of *if* or *should* ...
But its a matter of 'the bird is already out of the cage' so to speak:
AI is doing (and will eventually do what it currently cant), how should it best be handled/treated/used, and whats the best way to ensure something is actually authentic??

---
@JamesCaruso:
I just recently saw an article on that one myself.

 

[James K]

I also thought about this that could be a bit more 'scary' ....

Right now you have to seek out the chatbots (and I think even setup an account?) to use them.
But at some point someone is going to take that technology & make an "improved version" of the spam/troll-bots that go around posting crap on sites now.

 

[Jason N]

have you all seen the story about the Bing Version of GPT? how it "felt" scared because it couldn't remember a conversation?

 

[Jeff Wright]

Perhaps it could help with designing instruments to see structures inside clouds.

Passive millimetric wave cameras need to be in storm observation.

BTW, I just saw this latest example of radar tech:

Radar navigation for autonomous cars can 'see' through smoke, dust and fog

For autonomous cars to be able to navigate, their optic sensors—like cameras and laser—require a clear view. Now, researchers at Örebro University have successfully improved the precision in radar sensors for navigation to such a degree that the sensors can be used in autonomous cars, making...

techxplore.com

I bet it could let you X-ray a wedge to see vortices within if modified.

 

[James K]

@Jason N: No, didn't see that one but I did see an article on the Bing version giving rude or inappropriate replies.

 

[JamesCaruso]

I am interested in use cases or others’ experiences using ChatGPT for chase forecasting or general learning to support chasing.

My general understanding is that ChatGPT is not very good with narrow, specialized, technical domains. I tried creating a custom “storm chasing meteorologist” GPT (I think only paid OpenAI subscribers have this option). I then prompted it to synthesize SPC and applicable NWS office AFDs and produce a plain English forecast for the severe weather event on Monday 4/15/24. It referenced the site Outlook for Monday, April 15 | Severe Weather Outlook instead of SPC (the referenced site does contain the SPC convective outlook). There’s no sign of it using the NWS AFDs, and even when further prompted it appears to have searched only for an “Oklahoma” discussion. I tried to prompt it for target areas and times, and it was way too general. However, with subsequent prompting (and without feeding it further information about the event), it did come back with the following:

“Target Area:

1. Western Oklahoma and Northwest Texas: This area is delineated as having an enhanced risk for severe thunderstorms. The development of storms is likely influenced by the interaction of a dryline and an approaching cold front.
2. Specific Focus Points:
• Altus, Oklahoma, could serve as an effective staging area for chasers. It is situated near the expected intersection of significant surface features conducive to severe storm formation.
• Childress or Wichita Falls, Texas, are also potential targets, located close to the expected dryline activity and within the enhanced risk area.”

Any other experiences? I really just did this out of curiosity. I would not want to shortcut my own analysis and be fed a target, even if it were possible. But it would be useful if it could pull together text-based discussions from multiple sources, such as SPC and individual NWS office AFDs, even if just to put them verbatim into one response. Mainly, however, I would like to use ChatGPT more for learning about technical areas, radar interpretation, latest research on tornadogenesis, model biases, etc. I suspect its ability to search the web would make it useful for this purpose, but curious about others’ thoughts/experiences as to whether it “knows” enough to be useful in such a narrow technical domain.

EDIT: In the above target, I wonder if there is any actual use of granular forecast data, or just picking larger cities/towns as anchor points in the regions mentioned in the forecast discussions…

 

[Michael McClellan]

I am interested in use cases or others’ experiences using ChatGPT for chase forecasting or general learning to support chasing.

I've been using ChatGPT to supplement learning, but I treat all of the LLMs as extremely knowledgeable idiots. They "know" more than any of us ever could, yet often fail to correctly reason through even basic problems. Probably because, you know, they ain't actually thinking. As Skip said, they're parrots.

Here's an example of me asking GPT-3.5 why the dry air advecting from the desert southwest is referred to as the EML. Here's the response:


Is that actually a good answer? Maybe - feel free to let me know! - but I can't truly trust it. Notice that I led it to an answer I was inclined to believe as part of my second question. It's super easy to goad these LLMs into telling you what you want to hear; check out all those "news" stories of ChatGPT saying something awful, that usually leave out the dozens of subtly leading prompts that got the LLM to predictively answer based on the direction of the conversation. It's also why these LLMs make great role-playing companions... ahem, not that I'd know...

All of this to say, James, that I think it's still a bit too soon to rely on LLMs for honing in on target areas. It'll either be frustratingly vague, or only hone in on specifics once you lead it very carefully. And by then, you've probably already done the critical thinking yourself.

Now, generative models trained on actual radar and sounding data, programmed to highlight areas of interest on a map: much, MUCH more useful!

 

[Dan Robinson]

I've found AI to be quite useless so far for weather and chasing. It's basically a glorified search engine. I was planning on shooting upward lightning one night in western Missouri, and I asked it for the location of towers over 800 feet tall. It said "I don't have that information, but here is a link to the FAA tower database where you can look it up".

When I was working on the LCR script (LCR (vehicle Loss-of-Control Risk): A new winter weather parameter and scale (v1.2.1)) I tried using several AI engines to get something working. None could provide even one working script. Neither the C++ main script or the Python mapping script. All had numerous errors, and the debugging just went in circles. It would suggest a fix for an error, which would lead to another error, then another, then back to the original error to start all over.

I think it does OK for "mainstream" programming and other things, but anything even remotely specialized it just isn't there yet.

 

[Sam Soman]

I just told ChatGPT to write a song about a stormchaser.

View attachment 23386Verse 1: As the clouds roll in and the winds start to rise,
The stormchaser's heart begins to ignite.
He packs up his gear and hits the road,
Chasing the storm, his ultimate goal.

Chorus: Oh, stormchaser, fearless and bold
Racing across the landscape, uncontrolled.
Seeking the thrill of the raging storm,
He's always chasing, never warm.

Verse 2: The lightning flashes, the thunder roars,
The stormchaser's senses are heightened and raw.
He braves the gusts and the driving rain, Determined to capture it all, the pain
and the strain.

Chorus: Oh, stormchaser, fearless and bold,
Racing across the landscape, uncontrolled.
Seeking the thrill of the raging storm,
He's always chasing, never warm.

Bridge: He's a thrill seeker, an adrenaline junkie,
Chasing the storm, never feeling unlucky.
With a heart full of courage and a mind full of fire,
He's always chasing, never tired.

Chorus: Oh, stormchaser, fearless and bold,
Racing across the landscape, uncontrolled.
Seeking the thrill of the raging storm,
He's always chasing, never warm.

Love it man!!

 

[Steven Hanis]

As a newbie, I past in the convective outlook from the spc and tell it to rewrite to a highschool reading level.

 

[Sam Soman]

Congratulations!!!!