this post was submitted on 11 Jul 2025
13 points (84.2% liked)

Futurology

2984 readers
89 users here now

founded 2 years ago
MODERATORS
top 4 comments
sorted by: hot top controversial new old
[–] givesomefucks@lemmy.world 5 points 22 hours ago* (last edited 22 hours ago) (1 children)

We validated our framework through ex vivo experiments on cholecystectomy, a commonly practiced minimally invasive procedure, and conducted ablation studies to evaluate key components of the system.

I was going to say...

Even just properly identifying the gallbladder in a human body is incredibly impressive. But that's not what happened.

Like, they performed a "crucial part" of a gallbladder removal operation on gallbladders that had already been removed from the human body?

Did it tie a bow on it and light a candle?

Like most shit about AI, it sounds super impressive if you don't know what's happening...

[–] Lugh@futurology.today -1 points 22 hours ago (2 children)

It seems logical they would test it on extracted gall bladders first. Finding a gall bladder during surgery seems far from an insurmountable task for AI.

[–] Valmond@lemmy.world 1 points 17 hours ago

The article doesn't mention AI, but only a "framework" basically for moving.

Are you one of those who thinks "AI" will just solve lots of stuff?

[–] givesomefucks@lemmy.world 1 points 21 hours ago* (last edited 21 hours ago)

A cholecystectomy is removing a gall bladder...

So how crucial could a step be on the gall bladder after it was removed?

They're not removing healthy ones for transplants, it's something done on literal medical waste.

Finding a gall bladder during surgery seems far from an insurmountable task for AI.

It is incredibly difficult...

There is a shit ton of human variation, shits just crammed wherever and it all pretty much looks the same. We still beat AI by selecting traffic lights in a picture....

Analyzing a scan? Yeah, that's AI all day.

Real life? A human will keep winning for decades.