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.
Jump in the discussion.
No email address required.
Notes -
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:
My response:
Assessment:
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
It could do my job, but it currently can't. Not legally at any rate, and even if you can trivially quiz it for accurate medical knowledge, good luck getting a valid prescription out of it.
I don't make the rules, but a man's got to eat, and I might as well eat up while I can, because starvation is looming in my future.
I mean, even if I don't outright starve, I'd rather not end up with little or no money to my name. India certainly can't support any meaningful welfare for its populace, and while standards are low, people aren't going to be happy with settling for meals and little else.
The West can certainly do better, which is why I'm moving my ass there pronto in the hopes I can wrangle citizenship.
Take everything here with a pinch of salt because I'm hardly an expert:
India has always been a secondary consideration for foreign companies looking to perform manufacturing, and the only reason several large companies have started shifting substantial minorities of their production here is because of rising wages in China coupled with their self-induced geopolitical uncertainty.
In order for a country to successfully weather the shock of rapid automation, from my perspective it either needs a great deal of money to buy-in, or large numbers of existing factories that can be easily automated. The former describes the US and most of the West, and the latter describes China. I wouldn't be surprised if both entities managed to make it through with only modest disruption.
On the other hand, India has neither. When other countries begin automating faster than we can with our limited funds, the export value of our goods will drop (but so will the import costs of foreign goods?), reducing the value of our money greatly. We'll have to compete for raw resources that others can afford to pay significantly more for, given their grossly increased productivity.
Add in the effects of unemployment of highly skilled sections of the work force, the kind of people who bring in large amounts of foreign money, such as remote workers, and automation will strike from the top and work down. It'll take time for the government to afford an UBI, and the costs of keeping an increasingly large unproductive chunk of the populace fed will be debilitating.
I'm doubtful of the country's governance capitalizing on the benefits in time to outweigh the massive disruption it'll cause, but once again, I'm no expert.
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
I've actually come to the opposite conclusion, at least in the short term -- I've found that ChatGPT (4, unless otherwise specified) often understands the purpose and high-level practice of my job better than I do, but also can't do some of the simplest (to me) parts of my job. Concrete examples:
I had a nasty architectural problem in the application I work with, where the design was pulling the shape of the code in two incompatible directions. I gave ChatGPT some context on what directions the code was being pulled (think "REST vs RPC", if that means anything to you) and what considerations were causing the codebase to be pulled in those incompatible directions, and ChatGPT was able to suggest some frankly great changes to our process and codebase structure to alleviate that conflict.
I am trying to do a crash course in mechanistic interpretability for ML, and this involves reading a lot of dense, math-heavy research papers. My level of math expertise is "I took math classes in high school". Despite that, I was able to feed ChatGPT a paragraph of a research paper involving esoteric stuff about finite groups and representation theory, and it was able to explain the concepts to me on a level where I could implement, in code, demonstrations of the phenomena the paper was talking about (and understand exactly why my code worked).
When I was trying to understand "what happens if you literally just turn on backpropagation to train a language model on its own output, why doesn't that Just Work for solving the long-term memory problem?" I asked ChatGPT for 5 examples of things that would go wrong and search terms to look up to explain the academic research around each failure mode. And it did. And it was right, and looking up the search terms gave me a much deeper understanding than I had before.
On the flip side, ChatGPT is hilariously incapable of debugging stuff. For instance, when I provide it with code and a stack trace of an error, it suggests doing vaguely plausible actions that occasionally work but it kinda feels like a coincidence when they do. It honestly feels like working with a junior developer who struggles with basic concepts like "how does a for loop work".
I have also found that ChatGPT struggles quite a bit if I feed it a paragraph of an academic paper that makes a specific claim and ask it to come up with potential observations that would provide evidence against that claim. I've tried a bunch of different wordings of this task, without much success. I suspect that the reason for this is the same reason ChatGPT is so bad at debugging.
Specifically where I think ChatGPT falls down is in things that require a specific, gears-level understanding of how things work. What I mean by that is that sometimes, to truly understand a system, you have to be able to understand each individual part of the system, and then you have to understand how those parts fit together to determine the behavior of the system as a whole.
Where it excels is in solving problems where the strategy "look at similar problems in the past, see how those were solved, and suggest an analogous solution" works. It's really fucking amazing at analogies, and it has seen approximately every heuristic everyone has ever used in writing, so this strategy works sometimes even when you don't expect it to.
Still, "debugging stuff that is not working like the theory says it should" is a significant fraction of my job, and I suspect a significant part of many people's jobs. I don't think ChatGPT in its current form will directly replace people in those kinds of roles, and as such I don't think it would work as a drop-in replacement for most jobs. However, people who don't adapt can and probably will be left behind, as it's a pretty strong force multiplier.
I’ve found some of the same. I gave it a task of extrapolating the future of the Dune book series, and (it’s in my post history here) it failed miserably. The thing that struck me about the exercise is that it seems to struggle with understanding the pieces of the problem and what each wants to do. It knew of the Bene Gesseret, the Mentats, the space guild, and the houses, and even the events. But treating them as objects with intentions, or even putting the events of the past in order (it thought that the Butlerian Jihad was future in the timeline, rather than the past when it happened thousands of years before the answer I was seeking).
It’s generally smart enough to know which well-worn path to follow, but fails at looking at parts and extrapolating a conclusion.
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link