Submitted 10 months ago by fossilesque@mander.xyz to science_memes@mander.xyz
https://mander.xyz/pictrs/image/2033c44e-cb5e-4a76-8ca4-9ff866830305.jpeg
it baffles me that there are ID apps that don’t follow the model of 1) very clearly SUGGESTING what it MIGHT be, and 2) only present a level of precision it’s actually confident in
having it always present a specific species and just pick the most likely one is so dumb and irresponsible of the designers.
It’s a fundamental problem with the tech in general. It inherently has no concept of “I don’t know” and will just be confident, specific, and wrong.
That’s blatantly untrue. My plant ID app gives multiple suggestions with certainty percentages.
This is blatantly false. Classification tasks like this all have a level of certainty for each possible category - it’s just up to the person writing the software to interpret those levels of certainty in a way that’s useful to the user. Whether this is saying “I don’t know” when the certainties are too spread out, or providing a list of options like other people in this thread have said their apps do. The problem is that “100% certainty” comes off well with the general public, so there’s a financial incentive to make the system seem more certain than it is by using a layer (from memory it’s called Softmax?) that will return only the category with the highest degree of certainty.
uhhh do you have any clue how it actually works? i mean maybe there’s some sort of visual AI tech that doesn’t let you make it say “idk fam” but the standard stuff just gives a point value to each result, and you could just… have a minimum limit…
and like i’m pretty certain the current chatbots available generally are capable of responding that they don’t know, they’re certainly capable of “recognizing” when it’s a topic they’re not allowed to talk about.
This actually is a symptom from the sort of “beneficial” overfit in Deep Learning. As someone whose research is in low data, long tails, and few shot learning, there’s a few things that smaller networks did better in generalization, and one thing they particularly did better (without explicit training for it) is gauging uncertainty. This uncertainty is sometimes referred to as calibration. Calibrating deep networks can yield decent probabilities that can be used to show uncertainty.
There are other tricks for this. My favorite strategies prep the network for learning new things. Large margin training and the like are a good thing to look into. Having space in the output semantic space (the layer immediately before the output or earlier for encoder decoder style networks) allows for larger regions for distinct unknown values to be separated from the known ones, which helps inherently calibrate the network.
Oh so poisoning the elderly with hemlock was more common than just executing annoying philosophers eh ?
I don’t know who is using these things. If you’ve got a phone and a signal then you’ve got a shop. Go to it and buy the things you need.
I forage and hunt for food. It lets me get things I can’t get at the grocery store and it’s free.
I use them it helps me identify “weeds” so I can know if they’re good for pollinators or have to be removed immediately for invasiveness.
Example: I often keep a couple milkweed plants growing for monarch butterflies.
I would say that most people foraging wild plants in western societies aren’t doing it to sustain themselves. It is usually has to do with learning more about their surroundings, to revive old knowledge or for fun. And as long as you double check, play close attention to detail and most importantly don’t blindly follow an app you should be completely fine with this. (Well, foraging plants from the Apiaceae (the carrot family) is not really a good idea due to the close resemblance of most of its members.)
It’s for beginners. My son uses it to learn about plants in our yard.
It might be wrong, but that’s the next step of parenting.
Been using one of these apps to try to identify the many wild plants in my native pastures. Mostly just out of curiosity and conservation. Likewise it helped identify some trees and shrubs the previous owner planted around the yard.
They are far from perfect but are a good starting point as you get lots of pictures to compare to your mystery tree, you finish the job yourself.
What’s the joke? What was the plant?
PS: I get it now. Hemlock caises the ‘sardonic grin’
That doesn’t make sense? Hemlock causes flacid paralysis, while a sardonic grin is caused by ridgid paralysis. I really only associate sardonic grins with tetanus infections, maybe strychnine poisoning?
My app only says “dicot”
I came across a guy while walking in a park who began preaching to a friend and me about edible plants. It was real obvious he had no idea what he was talking about but was a socially awkward, lonely person desperately needing attention. I’m the friendliest person you will ever meet but felt an overwhelming desire to punch this man.
This was an awful story with an even worse conclusion
ThisIsAManWhoKnowsHowToGling@lemmy.dbzer0.com 10 months ago
I know nothing about plants.
FartsWithAnAccent@fedia.io 10 months ago
Yeah, I am not botanical enough to get this, but presumably it's something poisonous?
apfelwoiSchoppen@lemmy.world 10 months ago
Apiaceae, the carrot family, is full of wild species that are incredibly poisonous. Basically if it looks like a carrot in the wild dont eat it or you might die.
Ragnarok314159@sopuli.xyz 10 months ago
Look up “Sardonic Grin”. It’s one of those things that makes you think this is interesting, and also never going to eat wild plants again.
xantoxis@lemmy.world 10 months ago
Or hallucinogenic? Although if there were an easy-to-forage hallucinogen that looked like celery I’m pretty sure I’d know about it.
Chuymatt@beehaw.org 10 months ago
Hemlock, I believe.
rambling_lunatic@sh.itjust.works 10 months ago
Hemlock water-dropwort looks like celery. It causes muscle spasms, which at times results in the victim dying with a grin on their face.
Veritrax@lemmy.world 10 months ago
Looks pretty similar to hemlock.
gravitas_deficiency@sh.itjust.works 10 months ago
Neither do the LLMs you used to identify your “wild celery” lol