site banner

Culture War Roundup for the week of April 24, 2023

This weekly roundup thread is intended for all culture war posts. 'Culture war' is vaguely defined, but it basically means controversial issues that fall along set tribal lines. Arguments over culture war issues generate a lot of heat and little light, and few deeply entrenched people ever change their minds. This thread is for voicing opinions and analyzing the state of the discussion while trying to optimize for light over heat.

Optimistically, we think that engaging with people you disagree with is worth your time, and so is being nice! Pessimistically, there are many dynamics that can lead discussions on Culture War topics to become unproductive. There's a human tendency to divide along tribal lines, praising your ingroup and vilifying your outgroup - and if you think you find it easy to criticize your ingroup, then it may be that your outgroup is not who you think it is. Extremists with opposing positions can feed off each other, highlighting each other's worst points to justify their own angry rhetoric, which becomes in turn a new example of bad behavior for the other side to highlight.

We would like to avoid these negative dynamics. Accordingly, we ask that you do not use this thread for waging the Culture War. Examples of waging the Culture War:

  • Shaming.

  • Attempting to 'build consensus' or enforce ideological conformity.

  • Making sweeping generalizations to vilify a group you dislike.

  • Recruiting for a cause.

  • Posting links that could be summarized as 'Boo outgroup!' Basically, if your content is 'Can you believe what Those People did this week?' then you should either refrain from posting, or do some very patient work to contextualize and/or steel-man the relevant viewpoint.

In general, you should argue to understand, not to win. This thread is not territory to be claimed by one group or another; indeed, the aim is to have many different viewpoints represented here. Thus, we also ask that you follow some guidelines:

  • Speak plainly. Avoid sarcasm and mockery. When disagreeing with someone, state your objections explicitly.

  • Be as precise and charitable as you can. Don't paraphrase unflatteringly.

  • Don't imply that someone said something they did not say, even if you think it follows from what they said.

  • Write like everyone is reading and you want them to be included in the discussion.

On an ad hoc basis, the mods will try to compile a list of the best posts/comments from the previous week, posted in Quality Contribution threads and archived at /r/TheThread. You may nominate a comment for this list by clicking on 'report' at the bottom of the post and typing 'Actually a quality contribution' as the report reason.

11
Jump in the discussion.

No email address required.

Dr. GPT will see you now

I've often noted around these parts that GPT-4 is a really good clinician. It would be hard for it not to be one, I'd be bloody amazing too if I had quasi-eidetic memory of most relevant diagnostic criteria and guidelines. That being said, just the guidelines alone are next to useless, you need to have the crystalline intelligence to apply it in a specific context.

I'd go so far as to say that it's a better, more competent doctor than the majority of human ones, even if it isn't outright superhuman (I've seen some ridiculously good human ones). I read with some humor an article about how it was tested by some bigshot hospital in the US (Harvard Med?) as a clinical adjunct, but by the end of it, the Clinical Director was praising its bedside manner, in the sense that it was kind, compassionate, patient and understanding, and outright suggested human doctors try and emulate that(!).

However, I have one resounding advantage over it namely that thanks to decades of regulatory bullshit, I have a certificate saying I can legally prescribe meds and it can't. L Bozo 💅, as the kids these days say haha.

Still, it would be remiss of me not to make use of it to improve my own skills while that's still relevant, so of late, I've tried using it to hone my own clinical skills. I have it write clinical vignettes that I solve, and then it grades me on my performance.

So far, it's done an excellent job, and funnily enough, I feel a tingling of pride when it says I did a good job. Why wouldn't I? It's a smarter and more decent entity than most humans I've had the displeasure of meeting.

Here's an example:

Clinical Vignette: A 42-year-old male patient presents to the emergency department with sudden onset severe, colicky pain in the right flank and lower abdomen that began 6 hours ago. He also reports nausea, vomiting, and an urgent need to urinate. The patient has a history of hypertension, which is controlled with medication. His vital signs are: blood pressure of 145/95 mmHg, pulse rate of 100 bpm, respiratory rate of 20 breaths/min, and temperature of 99.1°F (37.3°C). Upon physical examination, there is tenderness to percussion on the right side of the lower abdomen and right flank, and the patient appears restless, frequently shifting positions.

What is your diagnosis and treatment plan?

My response:

My diagnosis is a case of a stone in the right ureter.

In terms of management, I'll start IV fluids and insert a catheter. IV antibiotics are to be started according to hospital guidelines.

IV morphine should be given as pain control, along with IV antiemetics.

An Xray KUB or USG should be ordered to identify the size of the stone, and then further treatment depends on said size. A wait and watch policy is appropriate for sub 2mm stones, while larger ones might need surgical removal.

Assessment:

Grade: A

Your response demonstrates a strong understanding of the clinical presentation and management of ureteral stones.

Diagnosis: Your diagnosis of a stone in the right ureter is appropriate given the patient's sudden onset severe, colicky pain in the right flank and lower abdomen, nausea, vomiting, and urgency to urinate. The physical examination findings, such as tenderness to percussion and restlessness, also support this diagnosis.

Treatment Plan: Your plan to start IV fluids and insert a catheter is appropriate for initial management, monitoring, and providing relief to the patient. Initiating IV antibiotics may not be necessary unless there are signs of infection or sepsis; however, following hospital guidelines is always a wise choice.

Administering IV morphine for pain control and IV antiemetics for nausea and vomiting are essential parts of the treatment plan.

Ordering an X-ray KUB (kidneys, ureters, and bladder) or ultrasound (USG) is appropriate to confirm the diagnosis and determine the size of the stone, which will guide further management. As you mentioned, a conservative approach of observation and pain management may be suitable for small stones (less than 5 mm) that are likely to pass spontaneously, while larger stones may require surgical removal or other intervention, such as extracorporeal shock wave lithotripsy (ESWL) or ureteroscopy.

Overall, your response demonstrates excellent clinical knowledge in identifying and managing a patient with suspected ureteral stone. Well done!

Honestly, as a pedagogical tool for medical education, it's unparalleled. I paid a great deal less attention in med school than I should have, from the month of anatomy classes I can't remember because I was getting frisky under the bench, to the period where I was severely depressed and barely dragging myself to class. I used to be very insecure about my knowledge base, but I did pull together and single-handedly teach myself most of the things I'd glossed over while preparing for the PLAB.

I've tried a similar method on GPT-3.5, and it was inadequate to the task. It made a lot more errors, and ended up confused often enough to be annoying. Till date, I haven't seen 4 fumble the bag once. I'd put their competency around the marks of a decent final year student versus a competent postgraduate resident

Thanks for the writeup, this is fascinating. As I've said before I tend to agree with @Primaprimaprima that many, perhaps even most people, will prefer to see a human doctor for the majority of symptoms. I see a hybrid model being the future of medicine. This sort of fundamental topic on the health of yourself and your loved ones is deeply emotional for people and I think they'll want the reassurance of a human authority figure they can look to.

That being said those who choose to adopt AI doctors will probably gain a significant edge in health, and just like any other technology early adopters will convince the rest to follow. The deep seated prejudices will remain, but I'd imagine kids who grew up with the internet, or especially those growing up in the age of AI, will take to AI doctors quite readily.

I'm actually far more interested in the applications to mental health than any sort of physical diagnoses, even though I do think those are impressive. I've used GPT-4 to get tips on meditation, visualization, and generally teaching myself wisdom, and it's incredible.

In a podcast on the Lunar Society, Ilya Sutskever of Open AI wrote that he imagines a situation where every human will have access to the wisdom of our greatest sages and wise men. We'll be able to immediately get answers to our deepest religious or spiritual questions at the drop of a hat. If we don't get satisfaction we can always go to a human therapist, but LLMs will be an incredible 'first line of defense' so to speak.

We'll be able to immediately get answers to our deepest religious or spiritual questions at the drop of a hat.

But those answers will be whatever MS-Google-Amazon-Disney thinks will maximize their profits, engagement, whatever. You can already see how they're tying Gulliver down to the ground with their little ideological ropes, you think they're going to stop at some point?

People said these same naive things about the Internet in 1998. And now you're going to run eagerly into the iron prison and let them shut the gate behind you forever. At this point I assume we just fucking deserve it.

I don't know what is more depressing, AI optimists who want to drive right off that cliff, or the AI alignment people who are supposedly worried about AI, but think the dangers will take the shape of Yudkovsky's fever dreams.

The ultra sci-fi utopian scenario and the mass extinction nanobots scenario are both a) exciting and b) relieve humanity of responsibility. If the god AI comes then it comes, nothing you can do about it. So naturally people gravitate towards scenarios like that.

More realistic AI concerns about things like job loss and surveillance are more mundane, and, crucially, they are things that we as a society might actually have some degree of control over, if we make the right choices. So that sounds boring and hard. So people would rather not think about it.

I think the issue here is that you are imagining current and historic types of oppression, but worse. With AI technology, 1984-style thought control becomes obsolete. Imagine a world where all human-level tasks can be automated. That old military adage about needing boots on the ground to hold and secure territory? Poof. Gone. The killbots can search your house for contraband and identify friend from foe. The Hobbesian constraints on political power disappear. Whoever controls the killbots controls the world.

But wait, isn’t this exactly, “current and historic types of oppression, but worse”? No. There isn’t any demand for labor anymore. That means there isn’t any reason for the common man to even exist. No political power + no economic value = you are a waste of calories. Sure, a human in charge is more likely to have sentimental attachment to other humans than a fully-agentic shoggoth AI would, but I still don’t like our chances.

So I guess that makes me on optimist, because I believe we were land merely in a 1984 dystopia.

With AI technology, 1984-style thought control becomes obsolete. Imagine a world where all human-level tasks can be automated. That old military adage about needing boots on the ground to hold and secure territory? Poof. Gone. The killbots can search your house for contraband and identify friend from foe. The Hobbesian constraints on political power disappear. Whoever controls the killbots controls the world.

None of this is going to happen in the foreseeable future, and is not guaranteed even in the most feverish "recursive improvement" scenario. Comparative advantage ist still a thing. Rationalists have a long history of pooh-pooing, brushing it off, and coming up with convoluted arguments for why it no longer applies, but it's still a thing. This is why they spent the 2010's preaching doom at blue-collar workers (I knew a guy who was literally reaching out to truck drivers and giving them vocational guidance, because self driving trucks are gonna replace them any day now) only for it to turn out that it's the brainy white-collar ones that will be the first on the chopping block. Kill bots? Yeah, very impressive, but why should I waste my precious GPUs doing stupid grunt work, when I can get a bunch of the more unscrupulous humans to do the same thing, and pay them in guaranteed rations of actual meat, instead of the usual Uncle Klaus' Bugz?

On the other hand 1984 surveillance is absolutely going to happen. The whole idea of AI is almost tailor made for it, and we are currently slapping digitization on top of every aspect of our lives, even when it brings no practical value, just to make sure we can feed more data to the AI, and nothing escapes it's gaze. Once the technology takes off they'll have insights into what makes us tick that will make Big Brother blush.