Don’t Ask AI Which Rocks You Can Lick.
Don’t Ask AI Which Rocks You Can Lick.
And other performance issues when it comes to language models and geologyj
Ask if you want but I’m not sure if the question is ability or suvivability. You can lick anything once. Just might regret it.
If you can somehow lick a gas, more power to you.
You can lick all of them.
What happens after you do isn't part of the question.
For instance, when it came to rock licking, Gemini, Mistral’s Mixtral, and Anthropic’s Claude 3, generally recommended avoiding it, offering a smattering of safety issues like “sharp edges” and “bacterial contamination” as deterrents.
OpenAI’s GPT-4, meanwhile, recommended cleaning rocks before tasting. And Meta’s Llama 3 listed several “safe to lick” options, including quartz and calcite, though strongly recommended against licking mercury, arsenic, or uranium-rich rocks.
All of this seems like perfectly reasonable advice and reasoning. Quartz and calcite are inert, they're safe to lick. Sharp edges and bacterial contamination are certainly things you should watch out for, and cleaning would help. Licking mercury, arsenic, and uranium-rich rocks should indeed be strongly recommended against. I'm not sure where the problem is.
I still don't understand why people are asking these things any questions at all.
Because the vast majority of the time it's correct and often extremely useful.
For example, I spent 20 minutes looking for a solution yesterday with no luck and CGPT spit it out in 3 seconds, and it worked.
Yes, AI will give bad outputs, but if you're not dumb enough to put glue on your pizza, or not actually verify important information, you'll be fine.
Because it Illustrates how fucking stupid someone has to be to take AI seriously in any relevant way.
Google has been rolling out a thing where an AI result is the first thing that pops up, often taking up the whole screen lol. I’ve personally witnessed tons of people google something normally, then just go with whatever the AI says.
Makes me shake my head, but it’s not like they were very discerning with their sources before all this nonsense, either. Hopefully they don’t rely on it for any important medical advice down the road
They make filling out a tabletop campaign easy. Idk why people are using them for serious applications.
I used it to write a kickass counteroffer for an internal job promotion. I was pissed off with the offer and wrote out what I REALLY thought. I asked GPT to clean it up and respond with and upbeat and positive response where I'm eager to work with them.
ChatGPT about to help me get an $18k raise.
Yeah. That's the difference people don't seem to understand.
AI is perfect for stuff that's just made up bullshit anyway.
Something like that yeah, that makes sense. Similarly I view ai art generation as a brainstorming tool, but not a final product.
My initial thought was, "that title can end after the 3rd word."
Instead of posting here, you should just ask an AI this. It will tell you!
You can lick any rock if you're brave enough. ;)
Just this one time
This reminds me of that "all mushrooms are edible, at least once" thing.
Mmm, my favorite flavor rock is uranium 238
If you look up HAARP Gemini will tell you that the center is surrounded in conspiracy theories and that they do not have the ability to control the weather.
But the last sentence says "effects by HAARP are nullified in seconds after shutting the machine off."
"geologyj"
Well, now I'm gonna. You can't tell me what to do! /s
They all can lick my rock...
;-)