this post was submitted on 31 Jan 2024
613 points (98.1% liked)
Funny
6799 readers
497 users here now
General rules:
- Be kind.
- All posts must make an attempt to be funny.
- Obey the general sh.itjust.works instance rules.
- No politics or political figures. There are plenty of other politics communities to choose from.
- Don't post anything grotesque or potentially illegal. Examples include pornography, gore, animal cruelty, inappropriate jokes involving kids, etc.
Exceptions may be made at the discretion of the mods.
founded 1 year ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
How does this even get discovered? Like they're pointing a camera at a croissant and the AI says "I don't know what that bread based food is but the guy holding it has melanoma". I just can't figure out how those two tests overlapped at all.
They likely changed the ~~model~~ AI and did some additional training on cancer data. The first thing you do in machine learning 101 is build ~~a neural network~~ an AI that can identify breast cancer. This is such a non story meant to mislead those who are not aware of how it works.
You realize most people are not aware of how it works, right?
Why else would I leave a comment explaining it? I did not mean to be condescending and hoped it was obvious my annoyance was at the article.
A guy/gal who studies cancer cells went to a bakery in Japan. (S)he quickly went, "if that computer can tell all these baked goods apart...."
I read an article about ages back.
I would imagine once it gets good at distinguishing things like various kinds of baked goods (which is actually really tough, I'd imagine), then you start exploring what other challenges it can solve.
I'm guessing something to do with either yeast or protein.