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

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.

Damn. I feel like laying pipe during labs would condition oneself to enjoy going to classes, if not being a general cure-all for depression. Pipetting dishes on the bench and piping bitches under them.

Cynicism can be a source of optimism.

As amazing as GPT is, I don't see it replacing doctors or knowledge workers in general anytime soon. Normie humans prefer dealing with other normie humans. GPT would need to be substantially better than a given knowledge worker to replace him or her, just as driverless cars would likely need to be substantially better than a given replacement-level driver for driverless cars to be widely accepted.

Furthermore, my personal suspicion is that a lot of the value-add (or "value-add") meat-bag knowledge workers bring is providing a face (and credentials) to build trust and a someone to potentially blame and/or sue when things go wrong: Human punching bags in waiting, bodies to throw under the bus when needed, soldiers to push onto grenades, corpses to stack in building terrain for shit to roll down-hill. Upon a failed pitch, a frustrated investment banking MD might chide an VP for poor process execution, who in turn blames an Associate for poor pitch-deck quality, who then reams an Analyst for a logo being the wrong shade of blue on slide 3 or a graph being misaligned on slide 33. Harder for an MD to blame an AI that cobbled together the memos and decks, without looking/feeling like a chump.

In the near future, I'd only expect GPT to provide greater scale for knowledge workers, as gamechangers ranging from Excel to TensorFlow have done. If you need DEI-related statements, GPT has got you fam. If you need code in some language in which you're not fluent, GPT will at least give you something that you can start with (sometimes even a robust solution, with well-named variables and everything). However, depending on country, I wouldn't be surprised if GPT gets outlawed in fields like medicine and finance under the guise of HIPAA-adjacent and confidential information concerns, respectively—if it's not already blocked/banned preemptively by a given employer along those lines.

I think that medical automation will be scrambled in as fast as feasible in at least India and the UK, for similar reasons.

The NHS is extremely costly, and also an unslayable albatross that no government can outright destroy and expect to win the next election.

As such, there's a massive impetus to cut costs, including avoiding paying for expensive consultants, replacing junior doctors with NPs/PAs that accept higher base pay for little to no career progression, using IMGs to prop up the NHS in working conditions the locals won't accept etc.

Pay erosion has prompted large strikes, still unresolved, in the UK by doctors. In response, the government has already pledged to attempt to automate as much of the NHS as possible, simply as a cost saving measure and as leverage against uppity doctors.

India too grapples with lack of access to healthcare, our public hospitals are heavily overburdened, and once awareness spreads of how effective AI is at the job, I expect rapid adoption.

And I suspect that the local populace will be quite accepting of it, better to have an AI doctor they suspect is worse than a human, versus no doctor at all, or very limited access to them.

The NHS is extremely costly

Compared to what? The UK spends less per capita on healthcare than many developed countries:

https://www.healthsystemtracker.org/chart-collection/health-spending-u-s-compare-countries/