In case you’ve ever wondered how to use a menstrual cup, don’t ask AI. They might give you a nightmare illustration.
But wait! There’s more! I decided to ask the Google AI to explain the diagram. It didn’t see any problem.
AI Overview
• This 3D medical animation illustrates a medical-grade silicone menstrual cup inserted into the vaginal canal to collect rather than absorb menstrual flow.
• The visualization highlights the proper sagittal view placement, emphasizing a comfortable position below the cervix and angled towards the sacrum.
• It serves as a reusable, eco-friendly alternative to traditional period products like pads and tampons, capable of being worn for 8–12 hours.
Now you know. Just punch the cup into the bladder and through your cervix to completely replace your uterus.
David Cronenberg himself couldn’t imagine this level of body horror.
What was your input query?
Proximity to that uvula doesn’t look comfortable. Maybe it’s a burst appendix; that would explain the hole.
What type of alien is this uterus in? Gray? Reptilian?
Icky, like so much of human biology, but not as bad as what you routinely see on The Pitt..
There seems to be entirely too much anatomy in the same position, in addition to the cervix cup borg horror and that plastic camera at the top. Spy ovaries? Digestive tract? Is that a kidney just floating around like a balloon?
It needs to work on those labeling lines. None of those bits are located within the vagina.
Wondering if this reflects a fundamental limitation of AI, an inability to “think” and reconstruct structures in 3-D?
Limitations of the query matter too, rorschach.
Obs no ‘thinking’, because it’s a LLM.
And whoever put the query in to generate the image also got it wrong.
(Still, I do like the verterbrae and the sacrum in the background. ;)
If you had an AI generate 100 images on a well worded query what would result? Pick the best 5 and worst 5. I always wonder if AI image horror shows are cherry picked from the worst results pile, though if bad stuff winds up in textbooks or research publications that’s not good.
I’ve had decent results in Canva with AI, though I have to cherry pick the best results after tweaking my instructions to get by the obtuseness of the language model. And sometimes the slop is more a feature than bug if it adds a subtle tincture of the uncanny or something humorously odd.
But asking AI to generate an image demonstrating insertion of a menstrual cup seems doomed to failure from the start. What is the “bladder” the image is pointing to?
What? No. I would iterate a given image, not select from a sample and be done.
Well, yes. With your approach, it would be.
Clearly this Abominable Intelligence fad is the future of humanity. It couldn’t possibly be a stupid waste of time with no value, oh no…
I use Google search a lot.
Many times a day at the very least. Already today I’ve used it to look up the latest membership declines of the SBC.
Lately in the last week or two, Google Search has gone way downhill.
I always check what the AI part at the top comes up with. Sometimes it is wildly wrong.
I put a query in the search box asking what percentage of Boomers voted for Kamala Harris.
It told me that it couldn’t answer because the 2024 election hadn’t happened yet.
I found Google Search easier and more reliable before Google started trying to insert their AI into everything.
That diagram is Horrifying! But, it’s not important. AI doesn’t care how many humans (women, men, children) it kills with its crap info and phony, destructive job displacement.
And, don’t you dare mention how many thousands of peoples’ lives are being destroyed by the berserk proliferation of data centers. The nashville zoo says it has animals that will probably die from the noise, power shortages, etc. of a data center to be built next door.
And whoever put the query in to generate the image also got it wrong.
Okay…care to tell us how one could get such a query “right?”
I’m not surprised Gemini found no problem with it. Current “state of the art” LLMs, with the notable exception of Qwen, are notoriously horrible at understanding images. They don’t actually get the images at all, just 1 token for each 16×16 block of a low resolution version of the image, often without any position information.
Iterate until unwanted elements of the image are removed and missing ones are added.
You seem stuck in a mindset of ‘tell it once’ and then it’s done.
Query is singular. The only thing the AI has rendered correctly is the menstrual cup. The anatomy is completely and utterly wrong in almost every detail. Nobody has vertebrae coming out of their hip. If it’s a saggital view, the sacrum and tailbone should be bisected and visible on the left. We won’t discuss the spycam, missing rectum, or the bone between the urethra and vagina.
Tethys, exactly.
Each prompt yields an image.
So one iterates. Still one (singular) prompt.
For example, one could append “If it’s a saggital view, the sacrum and tailbone should be bisected and visible on the left.” to the query that generated that image, so it would still be one query.
See? Whoever did that could tell that to the pre-trained generator.
Still one query, just not the one that was lacking that straight.
The competence of the human telling the bot what to do does matter, is the point.
AIs do not have agency or volition.
People just don’t get them: “AI doesn’t care how many humans (women, men, children) it kills with its crap info and phony, destructive job displacement.”
Correct, but misleading. It doesn’t care, period.
Again, no agency.
It does not do job displacement, people do that.
@ John
I understand that you find AI impressive. I personally prefer functional tools and abhor the uselessness and wastefulness of this tool. It’s certainly not an improvement on Grays Anatomy.
I also prefer a broom to an expensive gadget that consumes electricity and does a half assed job of sweeping the dirt off the floor.
John Morales @10
Fair point put in your trademark abrupt manner.
Could we both be right? Asking the wrong self-biased person I’m sure. Usually Canva AI generates results in sets of four. Reiterate upon the best of that? What happens when you reiterate upon shit? Shining a turd?
New technology, like the programmable computer back in the day.
Very, very early days. S-curve.
But yes.
Impressive that it can do, however poorly, what could only be done by intelligent beings of our kind.
People.
Another step up in automation technology.
Primitive as yet, of course.
Ah well.
It may be useless, but it’s apparently displacing jobs.
Has been for a while now.
Ahem. You can’t ask natural language questions of Gray’s Anatomy, nor does it replace it.
Huh. Most people use vacuum cleaners as routine, especially on carpet.
You are quite unusual in that.
Depends on your criteria.
I concurred that sticking to one query won’t work, and disputed that saying ‘generate 100 images from this query’ is the proper way to go about it.
Cute little token swipe, but kinda weak.
Who among us is not self-biased? ;)
Not reiterate. Iterate.
Right? Not repeat, advance.
Similar process to Newton’s method.
Not reiteration, iteration.
And why would one iterate shit?
What happens is one is shown to be shit at acumen.
Hey, your kinks are yours.
John Morales @22
I appreciate you are not reflexively against AI or LLM tools and push back a bit here against those who have strong anti-AI bias. So I concede that to you for sure.
Reference books in fact answer questions all the time.
No talking or electricity needed. I don’t see any value in a LLM that will give wildly wrong information to a query.
Just because corporations are firing human workers and replacing them with shitty AI tools really isn’t a glowing endorsement of the technology.
Fair enough, Hemidactylus.
Balancing the scales is not a bad way of putting it.
For sure there’s a financial bubble and a shitload of hype about generative LLMs that is not warranted.
I am not disputing that.
I own two vacuums that are useful, labor saving tools.
I don’t drag them out the vacuum to sweep, as the broom is easier, faster, and does a better job than the powered floor sweepers. (My vacuum does a great job, but it is not as easy as grabbing the broom and dustpan to sweep up whatever needs sweeping up)
If it’s easier to do a task with low or no tech, the tool isn’t worth its cost. Cost vs benefit is something the tech bros don’t seem to grok.
I’m sure that AI could be helpful and useful, but this is neither of those things.
Heh. Here is some perspective for you, Tethys:
https://etcjournal.com/2025/10/24/a-historical-perspective-on-the-pushback-against-ai/
Notably, posted on October 24, 2025. Still applicable.
I’m far more concerned about the massive amounts energy that AI uses (and the global warming thing) than the technology itself. Billionaire owned companies are using tax funded public utilities to run their private businesses while driving energy costs higher for consumers. This is problematic and shouldn’t be allowed. In its current state I find the costs far outweigh the benefits, unless one is an owner of an AI company.
I get it, it’s a talking point.
What you’re seeing is a rapid ramp up.
Anyway, topic is a bit vague when addressing detractors.
You get it could be purely sourced from renewables?
You get much of the problem is NYMBYism?
—
Put it this way: perhaps consider the comparative amount of energy and resources consumed by Trump’s Iran venture and associated costs; and then tell me about how building infrastructure for a new technology is somehow worse.
(maybe 300TWh or so vs 150 or so TWh)
Perspective. Stadia, holidays, cruise ships, outdoor heating, swimming pools…
I worry more about decarbonisation than about total energy budget, myself.
—
Thing is all this talk about energy use (and alleged water use, as if it vanished after use) is not about the technology. Or about its finances, either.
The tech is not the prob; if anything, its founders, implementers, and financers are.
(Domains)
The tech isn’t separate from its founders and it is in fact overtaxing the power utilities, which are built at the public’s expense. Empowering robber barons doesn’t benefit anyone in the long term.
It would be better if the billionaires were required to build the necessary power infrastructure for their data centers, and did it with renewable resources.
Hm. An interesting proposition.
How not so?
(Is math not separate from its founders? Physics? Steam Engines?)
Um. That is not the tech. That is those who are financing it.
Not really. Again: “What you’re seeing is a rapid ramp up”.
Precisely. As I just said.
But that is also not the tech.
As for ‘billionaires’ as a class, I offer Oprah Winfrey: https://www.forbes.com/profile/oprah-winfrey/
↓
$3.4B Real Time Net Worth
as of 6/13/26
#1249 in the world today
Point is that investing is not wasting.
War is waste.
Want to add the wars in Ukraine and in Sudan and elsewhere for waste of resources?
What about cruise liners?
They are not infrastructure.
Datacenters are.
Power plants are infrastructure John, stop being obtuse. Oprah Winfrey isn’t one of the Tech billionaires that are being heavily subsidized by the taxpayers to implement a technology that primarily benefits their tech companies.
Non coincidentally, the tech bros are morally reprehensible men who support the toxic clown and his fascism, aka the modern day robber barons.
Who backed JD Vance and has recently moved his entire family from California to South America? Who campaigned with the known rapist and was allowed to initiate DOGE? Who financed a rapist for POTUS?
Well, we’ve come a long way from that image and PZ’s query to a bot, Tethys.
Evil billionaire tech bros, got it.
Here, this should make you happy, being a bit of a concession of oopsies:
https://www.reuters.com/business/metas-zuckerberg-admits-mistakes-made-ai-transformation-2026-06-12/
↓
In the memo, Zuckerberg describes the rapid advances in AI and the challenges brought on by the boom in the technology.
“Given the complexity of these changes, we’ve made mistakes and will almost certainly make more,” Zuckerberg said, adding that he is also “focused on providing as much stability as possible” in terms of organization changes going forward.
“I don’t want to overpromise because the world is changing in ways that are out of our control,” he said, reiterating that Meta does not expect more company-wide layoffs this year.
He said Meta will try to find new roles for employees reassigned to train AI models, after the Facebook owner carried out a massive restructuring in May, laying off 10% of its workforce globally and transferring 7,000 employees to new initiatives related to AI workflows.
Aaaah!
Oh my god, noooooo!
Aaaaaaaaaaaaargh! Urk!
Slides to floor unconscious.