Live data from Hacker News

Mushroom hunting with LLMs: what can go wrong?

quesma.com

51–60 of 81 posts

Re: Mushroom hunting with LLMs: what can go wrong?

#51

Chanterelles and false chanterelles are especially tricky. They fruit at the same time in the same areas. I have to do a 2nd pass after I have washed and dried my haul. https://www.mushroom-appreciation.com/wp-content/uploads/202...

The false chanterelle that I know is not poisonous.

Re: Mushroom hunting with LLMs: what can go wrong?

#52

Ha! I just had a very interesting conversation with ChatGPT about a mushroom that I found in my front lawn. I am 99% sure it was an edible oyster mushroom which included analysis the of the size, growing substrate (dead ash tree root which turns out to be a useful identifying characteristic -- I learned a lot about mycology in a short time). Plus I don't use fertilizers, herbicide, pesticides, fungicides (obviously)…

This time of year it is common for folks to mistake Dear mushrooms (Pluteus cervinus) with the poisonous juvenile invasive Amanita family.

Amanita travels everywhere with wood mulch around local gardens, and is practically impossible to get rid of once established.

Stay safe, and never believe your own lying eyes when it comes to mycology. Could join a local university hosted public outreach foraging club, as the experts enjoy nothing more that spotting weird looking finds. =3

Re: Mushroom hunting with LLMs: what can go wrong?

#53
post #6

I think the more important question is: have people really run out of interesting flavors at their local stores and restaurants, that they are so obsessed with eating things they find growing on the ground? I’ll never understand mushroom culture.

I had a friend that was quite passionate about foraging for mushrooms while we were in high school. He eventually went on to receive a PhD. in mycology. My old friend as well as everyone else I knew that liked to forage mushrooms were... uh... not looking for "flavorful" mushrooms to say the least.

Re: Mushroom hunting with LLMs: what can go wrong?

#54

There's been a spike in cases of people eating death cap mushrooms in California this year, and I would bet almost anything that LLM adoption has something to do with it.

They look like the Asian Paddy Straw Mushrooms, so people used to collecting those, being new to the area and not knowing about the Death Cap run afoul of it. The San Francisco Chronicle often has stories about this after it rains.

Re: Mushroom hunting with LLMs: what can go wrong?

#56

Chanterelles and false chanterelles are especially tricky. They fruit at the same time in the same areas. I have to do a 2nd pass after I have washed and dried my haul. https://www.mushroom-appreciation.com/wp-content/uploads/202...

Do the false chanterelles that you encounter smell similar to chanterelles?

Re: Mushroom hunting with LLMs: what can go wrong?

#57

Earlier quoted context omitted.

Some mushrooms like chanterelles can't be reliably farmed, and are quite tasty! I love being able to spend a day hiking and coming back with a meal.

Morels are starting to make good progress in being farmed. But, I still enjoy the hunt every spring.

They're still on my bucket list to find. Lots of false morels around here. :(

Re: Mushroom hunting with LLMs: what can go wrong?

#58

Ha! I just had a very interesting conversation with ChatGPT about a mushroom that I found in my front lawn. I am 99% sure it was an edible oyster mushroom which included analysis the of the size, growing substrate (dead ash tree root which turns out to be a useful identifying characteristic -- I learned a lot about mycology in a short time). Plus I don't use fertilizers, herbicide, pesticides, fungicides (obviously)…

oysters are pretty safe

Yes but you need to be sure it is an Oyster Mushroom in the first place.

Re: Mushroom hunting with LLMs: what can go wrong?

#59

Is it possible to reliably (>99%) identify mushrooms from a single image, with any method? All image datasets have an intrinsic minimum error that comes from the limit of information in the data, regardless of what model or method you use to analyze it. You might not be able to tell apart two similar-looking mushroom species just by looking.

Certainly it's not possible, yeah. A better test might be to have the AI report either confirmed good, confirmed toxic, or unknown. Even an experienced mushroom hunter needs to humbly put many mushrooms into the "unknown" category.

Re: Mushroom hunting with LLMs: what can go wrong?

#60

Chanterelles and false chanterelles are especially tricky. They fruit at the same time in the same areas. I have to do a 2nd pass after I have washed and dried my haul. https://www.mushroom-appreciation.com/wp-content/uploads/202...

The false chanterelle that I know is not poisonous.

https://en.wikipedia.org/wiki/Hygrophoropsis_aurantiaca#Edib...

The real thing is plentiful enough I don't mess with them, but I know people that regularly eat the false ones.

Post reply on HN