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.

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.

Or hallucinogenic? Although if there were an easy-to-forage hallucinogen that looked like celery I'm pretty sure I'd know about it.

Hemlock, I believe.

Hemlock water-dropwort looks like celery. It causes muscle spasms, which at times results in the victim dying with a grin on their face.

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.