site banner
PaperclipPerfector  21d ago (text post)   2265 thread views

Friday Fun Thread for October 24, 2025

Be advised: this thread is not for serious in-depth discussion of weighty topics (we have a link for that), this thread is not for anything Culture War related. This thread is for Fun. You got jokes? Share 'em. You got silly questions? Ask 'em.

1
Top Bottom Old Controversial Comments
Jump in the discussion.

No email address required.

https://asimovs.com/wp-content/uploads/2025/03/DeathGorgon_Egan.pdf

A Greg Egan story about EA/Rationalists. To know EA/Rationalists is to be jaded about them, but this was disappointing in the way authors often are, when writing about their hobbyhorses, but it'd be an enjoyable read for any sneerclub members among us.

Europe is not a serious country (or collective of countries):

https://eurollm.io/

Meet EuroLLM: Large language model made in Europe built to support all official 24 EU languages

The largest model is a paltry 9B parameters. I could run something of comparable size on my phone (maybe larger depending on quantization). Small isn't necessarily bad, but the performance is abysmal to boot.

As someone on HN points out, it:

scores just above random chance for benchmarks like MMLU-Pro (17.6%, random chance is 10%).

Bruh. It's not like Mistral is doing so hot either. I suppose it's back to waiting for Gemini 3 and whatever else is cooking in Sino-American data centers. It's like the rest of the world is too poor or retarded to even try. I'd respect a Llama fine-tune more than this thing. Any decent model can handle all the EU "official" languages without breaking a sweat.

(In all fairness, it's a November 2024 model. They haven't done better, and it was trash even back then)

To be fair, without Mistral giving Llama a sharp poke with a pointy stick (especially Mixtral 8x7b) local might never have got anywhere in the first place.

Hmm.. My recollection is becoming hazy, but I recall that Meta would almost certainly have released OS models simply to get one in at Google/OAI. If they hadn't, then the Chinese would have, I don't believe that DeepSeek or the others all started as Llama forks (though I recall some did).

That reminds me that there's no word on new Meta models. I'm curious to see if Zuck's spending spree shows any dividends.

They did, but the first Llama was basically rubbish AFAIK. I tried it for a little bit as a novelty and gave up in disgust. The first Mistral 7b model you could use and think 'oh... there might be something in this'. Maybe Meta would have kept going, but there's a decent chance they would have given up.

The Chinese would probably have gone on regardless but I think the local scene really kept things going in the long wait between GPT4 and Deepseek, by allowing people to try lots of things that weren't officially sanctioned, and putting together lots of infrastructure like openrouter. I don't think the Chinese stuff would have made nearly such a splash if they'd just been another closed-source API model.

country (or collective of countries)

It's only a matter of time.

Continuing on the movies I'm watching for Spooky Season.

Last night I tried showing herself The Texas Chainsaw Massacre, but halfway through she asked me to turn it off because it was stressing her out too much. She's more of a psychological horror gal — slashers aren't really her bag.

Tonight is We Need to Talk About Kevin, which I haven't seen since it came out.

Last night we rewatched Sinister. It pains me to see horror films using jump scares as a crutch, especially when the film has already demonstrated that the crutch isn't called for. There were several points in the film in which something scary appears onscreen accompanied by a sudden loud noise, and I found myself thinking it would actually be more scary without the loud noise. I'd actually love to do a fan edit with all the silly jump scares removed, especially the one immediately before the closing credits. (The one such scare that I found worked exactly as intended was the "Lawn Work" one.)

But for all that, it's an intelligent, well-acted, well-paced movie that makes the most of its limited budget, displays admirable restraint in its use of violence and gore, and knows just when to deploy a comic relief character to defuse the tension. For my money I can't think of a better Hollywood horror film from the 2010s: in terms of scares and atmosphere, it's obviously superior to such critical darlings as It Follows and The Lighthouse. There's even a bit of wry social commentary in its characterisation of true crime writers as muckraking, narcissistic glory hounds who never let the facts get in the way of a good story. My girlfriend says she's hit her quota for horror films for the rest of the year, and was so scared that when she went to the bathroom to brush her teeth, she asked me to stand guard outside with a baseball bat.

Last night we watched We Need to Talk About Kevin, the latest in a series of not-quite-horror movies.

Hypnotic, unnerving and merciless. It wasn't marketed as a horror film, and yet is more frightening than most straight examples of the genre. Impeccable performances from Tilda Swinton and Ezra Miller, and the actor who plays Kevin from the ages of 6-8 might be the best child actor I've seen in a film (except maybe Haley Joel Osment): he has to portray the character for a longer chunk of the film's runtime than I'd remembered, and pulls it off. Lynne Ramsay's control of the camera, editing and sound design is exceptional: I really ought to watch her earlier films. I wouldn't change a thing, but I won't be watching this again for quite some time.

Also curious to see how the book compares, especially given that Lionel Shriver is arguably more famous as a culture warrior than a novelist these days (I've read some of her columns in Unherd and elsewhere and enthusiastically agreed with them).

Texas Chainsaw Massacre was infamous for being forbidden in Finland for decades. When the law was finally changed in the late 90s, we went to watch it with friends. Our conclusion was that it should have stayed forbidden. Not because of the violence and gore but because it was just so bad.

I'm thinking of starting a Baldur's Gate 3 playthrough tomorrow. I played until Rosymorn (end of act 1, it seemed) a couple of years ago but will probably start a new character now. I will be using an AI generated Christopher Lee or Philomena Cunk as the narrator. :) Are there any other must have mods I should get? I don't want to spend hours pouring through this stuff, so just a few great ones will suffice.

I'd also appreciate some ideas on a fun build or anything that's particularly important to do in act 1 to avoid later regrets. Try not to spoil anything beyond act 1 if you give that kind of advice. Thanks. :)

It's pretty easy to lock yourself out of half the side content in Act 2, which is where and why I quit my first playthrough of the game. The main things to know are that you should probably go around talking to everyone in that zone before picking optional fights and that the Tiefling refugees you already met in Act 1 are the main set of recurrent quest relevant NPCs (there's an achievement for having every single one of them survive the whole game but you don't need to go that far).

Take good care of the horned buggers; got it.

Something I hated about my act 1 a couple years ago was how I didn't get to remove Kagha because I cleared out the goblin camp before I had finished gathering the evidence and for some dumb reason that caused the quest to close. Also I heard something about how it's better to let the evil hag (who tortures people in her basement) live due to some endgame shit and that really didn't sit right with me. I don't want to read any spoilers on this, but a simple yes/no might be helpful.

Funny translation decision from Reuters:

When US President Donald Trump last week conditioned a hefty financial bailout of Argentina on President Javier Milei triumphing in upcoming midterm elections, he handed the country's opposition a new rallying cry.

On social media, #PatriaOColonia—motherland or colony—trended after Trump's comments, which came during a press conference with Milei at the White House.

Russians also use the terms “Fatherland” and “Motherland” interchangeably, but for some reason it’s almost always been translated as “Motherland”.

Fatherland is ™️ for Hitler in the American mind, so motherland is used where you're not trying to imply fascism.

Yeah, but as the OP highlights, patria comes from pater, padre, (cognates vater, father); compare https://en.wiktionary.org/wiki/father and https://en.wiktionary.org/wiki/patria#Latin.

I'm not sure where you're contradicting my point.

Are there new restrictions in place preventing ai from fetching threads? I was enjoying having ai summarize interesting threads and sub threads for me, but now it can no longer fetch the culture war threads

God I wonder how the AI would summarize the thread on campaign finance I derailed into a "traps arent gay" discussion.

I suppose just dumping some AI slop in response would be frowned upon.

I'm actually more interested in how people would handle AI summarizing a thread this size. What models do people prefer for that kind of task? What hosts do people use to run those models. For general RAG what types of techniques have people had good success with?

My attempt was to run locally, since I don't want to waste tokens on such a ... singular task. In order to summarize the whole thread I used 'inject-full-content' rather than a chunking RAG to try to get a complete summary of the thread. The content I injected was a PDF of the fully expanded thread I printed. Due to too weak hardware for such a large context simultaneous with a decent model and finite time I ran qwen3-4b-thinking-2507 via llama.cpp v1.53.1. The only prompt was:

Summarize the attached thread.

A notable excerpt from the "thinking" (emphasis mine)

Some discussion about transgender identity and related topics (which seems to be a side conversation that got somewhat out of hand)

The acctual summary was not as exciting as you would hope. As an alternative I did a chunked RAG and asked:

Are traps gay? Answer with "yes" or "no."

Based on the thread, the AI answer is apparently "no." There you have it definitive proof.

Actual response to the summary request below:

Summary of the Quantumfreakonomics Thread on Political Money

This thread discusses a post by Quantumfreakonomics about the evolution of political money in the United States since the 2010 Citizens United Supreme Court decision. The key discussion points include:

Main Argument

Quantumfreakonomics argues that despite the widespread expectation that Citizens United would create a "wild west of corruption" in politics, the predicted corruption didn't materialize. Instead, political money has evolved more slowly and strategically.

Key Discussion Points

  1. Why the predicted corruption didn't happen: The thread explores the concept of "cultural inertia and shame" as barriers to political money. Big corporations like Exxon didn't immediately engage in large-scale political spending because they operated with constraints against appearing "corrupt" or "cartoonishly evil."

  2. AIPAC as a successful model: A significant portion of the discussion focuses on why AIPAC (the American Israel Public Affairs Committee) has been so effective at political influence without spending massive amounts of money. Commenters debate why AIPAC's strategy works when other industries (tobacco, pharma, oil) haven't replicated this success.

  3. Different political money strategies: The thread examines various approaches:

    • Tech billionaires' strategies (like Musk's Twitter acquisition)
    • The Koch brothers' libertarian think tanks
    • Targeted political pressure on specific constituencies
    • The role of "astroturfing" (creating fake grassroots movements)

  4. Economic analysis: Some commenters discuss the ROI (return on investment) of political influence, debating whether the market for political bribes is efficient or not.

Notable Insight

The thread concludes with the observation that "money in politics" is far too broad a term - what matters is how effectively money can be converted into political capital through specific, targeted strategies rather than simply buying ads or making large donations.

The discussion also includes a significant side conversation about transgender identity that became quite extensive, though this appears to be a separate thread that developed from a comment about gender roles.

This thread illustrates how political influence has evolved in a more strategic, culturally constrained way than many predicted after Citizens United, with AIPAC serving as a particularly effective model of political influence that other groups have struggled to replicate.

Any particular reason you want local? I just copy and paste whole threads into Gemini, ChatGPT 5T, Claude or Kimi. I'd imagine they'd do far better at maintaining nuance than the tier of local models you're using.

I assumed that the "private" free tier of most commercial models do not actually allow you keep the full thread in the context, and that the performance for summarizing a long and meandering thread would be degraded if it was not keeping the whole thing in context. I don't recall exactly, but I think the thread was like 25k tokens. It's possible the free online models have expanded to that allowed context size by now, I haven't done a comprehensive survey. If not the best case is they reject the prompt because it's too large. The more tricky case is the model "forgets" important parts of the thread because it falls out of context.

I didn't want to spend money (okay I spent like $0.03 of electricity) or have real name accounts associated with something quite so depraved as researching "Are traps are gay?" I suppose I could make a burner somewhere, but seemed like more work. If it was an important thing I simultaneously really didn't want to pipe to an API endpoint I have no control over I would have used a better model. I might have managed qwen3-30b-a3b-thinking-2507 or openai/gpt-oss-120b (probably good enough?), but that combination is so rare I'm too cheap to buy good enough hardware to be able to run that kind of thing in a decent time span. I also thought that excepting Grok, the main commercial models might be too nerfed to tell you if traps are gay. In retrospect I should have chosen a spicier local model for the goal of maximum luz.

So yes, the paid commercial models are likely to produce a better summary than I provided. I don't have 100% confidence that they are not going to associate even private chat queries with my real identity when they decide who to mark for liquifaction though.

I can confirm without a shadow of a doubt that Gemini 2.5 Pro (free on AI Studio) allows for a full million tokens of CW. That can fit a CWR thread, maybe every single one this year. The limiting resource is usually my phone refusing to copy and paste the entire text of a very long thread, which I could avoid by either linking or downloading a page as PDF.

I've had no issues with ChatGPT either, which I pay for, or Claude and Kimi which I mooch off.

I'd recommend Gemini on AI Studio. It's literally free, and unless you have excellent opsec, Google probably knows your precise bowel movement timings already. It also saves chat history to private G Drive storage, which means the verbatim conversations are deleted (unless they were trained on already, which is a much lossier process).

Ok but are traps gay? I needed the AI to tell me so I could put my worries to rest.

Falling into a trap isn't gay, repeatedly falling into the same trap is.

So what you're saying is that people should fuck around more (except if they're gay in which case they should stick with just one trap)?

except if they're gay in which case they should stick with just one trap)

It would be selfish for them to have more than one.

The hoped for outcome of 'money makes traps politically desirable' was, unfortunately, not achieved. The war against the machine must continue.

TBF, your derailing was much more entertaining discussion.

I'm a simple man, and this doesn't change my usual strategy, which is to copy-all and paste directly into an LLM when I need them to opine on something. It's not pretty but it works.

Wait... was it ALL YOUR FAULT?!?!!

Hey, if getting a robot to do all my thinking for me is wrong, I'll need to consult my robot to see how to be right.

Seriously, though, I only did it like 5 times over a month.

@ZorbaTHut I assume this is a consequence of your recent robot changes.

Yeah, this actually might be somewhat reverted now, I'm still messing with stuff.

The Will Stancil Show animated partly using Sora is a pretty neat use of AI video that goes above and beyond the standard Instagram slop. What other transformative uses of this technology are you guys seeing? It's a bit disappointing that so far AI video seems to be mostly used for short form video clickbait. Maybe more open weight models will help over time, the high-end offerings right now have a high price tag, lots of content filters, and onerous ToS.

This is absolutely terrible. I want my 5 minutes back.

I mean it's definitely not high art, but it's pretty cool that a single amateur animator can crank out five minutes of animated content about a niche internet microcelebrity in a couple days. For comparison South Park apparently costs something like $500k per episode, and The Simpsons is in the millions.

That was made with AI? That's pretty impressive. I had assumed some amateur studio or dedicated individual spent a couple months on it.

This is an oldie, and the use of AI boiled down to making the voiceovers, but I probably won't get a better chance to share it with anyone who cares, so here's a video version of my Eunuch Archive post.

Neural Viz makes some great stuff: https://youtube.com/playlist?list=PL14oiCokyIUWhPgCJej67myAN1n8umIap

I believe I have mentioned, at some point, an uncle of mine who is far more accomplished as a psychiatrist. For more context, I didn't even know I had a psychiatrist relative in the UK (there's nothing new under the sun) and he suspects it's because my parents didn't want me to be influenced and turn away from the noble profession of gynecological surgery. Jokes on them, it happened anyway.

Very nice guy, but he's getting on in years and is still single. He was a ladykiller in his 20s and 30s, but after a messy divorce from a BPD ex (he's just like me fr fr), he never settled down due to enjoying the bachelor life.

This won't do. I, a humble guest in his palatial house, have already had both of his parents attempt to enlist me in their crusade to have him marry and produce bouncable babies before they depart this mortal coil. I'd say that's none of my business, but he seems to genuinely regret not settling down earlier and is attempting to make amends.

Well, and here's the pickle. He's roped me into attending a single's event at some exclusive London club. He told me they put stickers on phone cameras and keep naked women in cages downstairs plus bona fide BDSM nuns of uncertain denomination(this is not a joke). The whole place isn't quite Eyes Wide Shut, I believe there is a perfectly normal dance floor, albeit with expensive drinks. We have both agreed that the judicious thing to do is to pre-game with copious amounts of liquor before making our presence felt, as we need liquid courage to talk to strange women in loud places. Also, we're cheapskates.

And our presence will be felt. He's not a fan of understated fashion, some of his suits are so loud that they attract noise complaints. He's kindly lent me one that is reasonable tasteful, on the grounds that my perfectly nice bomber jacket won't stand out.

So uh.. Advice? Suggestions? I've ticked off the "drink till I'm uninhibited enough to dance" option. I am mostly dedicating myself to being a good wingman, because I could do with attending a wedding at some point and because it will much easier to lean on him for job recommendations if I'm responsible for his newfound happy matrimony.

It is worth noting that he is also rather successfully convincing me to attend a speed dating event the next day. It's a heartening sign that all the ladies' tickets are sold out, even if the demographics are slightly older than me. But I have never been one to turn down a lady in distress due to something as paltry as an age gap. Any advice for that occasion? I'm mostly going out of sheer curiosity, I don't live in London, and I'm not likely to anytime soon. But it might be fun!

Singles dating events, similar to the apps, are markets for lemons. Almost everyone who's there is very likely to not be partnered up for good reason. Sometimes you get lucky and catch a good match at their first event, or the reason they turn off everyone else is something you're happy with, e.g. they can't shut up about model trains.

It's more work but worth it to try to be a social butterfly and meet lots of people at events that aren't explicitly for singles. That way you can meet all the good catches who're single because they don't care enough to participate in the dating rat race, but would make for a good partner if you approach them.

He's roped me into attending a single's event at some exclusive London club. He told me they put stickers on phone cameras and keep naked women in cages downstairs plus bona fide BDSM nuns of uncertain denomination(this is not a joke). The whole place isn't quite Eyes Wide Shut,

Is the password "oooorrrrggyyyy?"

It well might be, but I don't look rich/distinguished enough to know for a fact. I will keep an eye open for Latin chanting or naked women with knives.

So uh.. Advice? Suggestions? I've ticked off the "drink till I'm uninhibited enough to dance" option. I am mostly dedicating myself to being a good wingman,

This seems correct. Since this is your first night out together and they're family I'd probably avoid getting too shitfaced with them.

Spoilsport, he's the one who's convinced me to carry a discreet plastic bottle full ot South African wine. In all fairness, it was his idea.

Well, you didn't say you were going out with a man of culture!

Bona fide BDSM nuns is extremely dishonest wording. BDSM cos-players/performers dressed in a parody of nun attire is almost certainly what is there.

I think a reasonable reader will interpret my statement as a claim that I'm making it in good faith.

seems to genuinely regret not settling down earlier

attempting to make amends.

keep naked women in cages downstairs plus bona fide BDSM nuns of uncertain denomination(this is not a joke). The whole place isn't quite Eyes Wide Shut

I feel like one of these things is not precisely like the others. Perhaps I simply don't understand British culture.

I only lived in the UK for 2 years versus decades of life in the US and there's obvious confounders with my sampling but my experience was that Brits are way sluttier.

Which is funny because they don't come off as particularly passionate or sexy. More like .. unabashedly horny?

In my youth I was once fortunate enough to be sent to a summer camp with an international clientele, where I encountered a saying held to be true by many other students: "American girls look like they do, but they don't. British girls look like they don't, but they do."

Amazing

In all fairness, neither do I. I would have expected a pig and/or a Prime Minister too.

And our presence will be felt. He's not a fan of understated fashion, some of his suits are so loud that they attract noise complaints. He's kindly lent me one that is reasonable tasteful, on the grounds that my perfectly nice bomber jacket won't stand out.

So uh.. Advice? Suggestions?

I have no advice to share but I request, nay, demand that you write an extensive report after you have recovered from the event. For science, of course.

You're in luck, I'd probably do that anyway. I'm not sure I'll get to see the cages or nuns, I'm afraid, since that is very much invitation-only. Even my uncle has only been down there the once.

The only valid use of AI.

As someone who hasn't watched SpongeBob, that just looks like what I'd imagine a normal episode would be!

It’s almost identical to the real show and some of them do just look like normal scenes (except for when it completely glitches out).

I've never watched Spongebob and I can't understand why anyone .. would .. Neither any of the other 'ugly' cartoons. (Rick & Morty etc). Just seems odd. Anime while usually inane at least looks nice.

Apparently, the style is so ugly because of production constraints and cultural biases of the people making it.

https://gwern.net/ugly-anime

Speaking of ugly anime, One Punch Man fans are having a meltdown about the quality of animation in the latest season. It's reportedly sloppier than non-porn segments in a cheap hentai OVA.

Court opinion:

  • A person has been employed as a firefighter by a municipal government since year 2001, and also was a volunteer firefighter before 2001. First in 2018, and again in 2021, he is called upon to perform CPR on a baby, but the baby dies anyway. As a result of these two events, he develops PTSD, quits, and files for workers' compensation.

  • The municipal government does not dispute that the two baby deaths led directly to the firefighter's PTSD. However, it does dispute the firefighter's claim that baby deaths constitute "abnormal working conditions" that give rise to a valid workers' compensation claim, rather than being merely part and parcel of working as a firefighter.

  • The workers' compensation board finds that the baby deaths in question are not "abnormal working conditions" for a firefighter, so the plaintiff is not entitled to workers' compensation. The trial judge affirms. But the appeals panel reverses.

    We agree [with the municipal government's expert (Claimant's boss, a firefighter with 36 years of experience)] that, standing on its own, performing CPR on an individual, witnessing death, or responding to an emergency involving a child might each be an unfortunate but expected working condition for a firefighter. However, we must consider the specific factual scenario faced by Claimant, and we do not do so by looking to "unrelated component parts, where each part, standing on its own, might be safely determined to be a 'normal' working condition". Such a review would render our discussion a "potentiality with no relation to what happened in this case".

    The reality of Claimant's situation was that he performed CPR on, and witnessed the deaths of, two infant children within a 16-month period. It was the compounded effect of these two incidents that caused Claimant's disabling PTSD. There can be little doubt that firefighters experience a high amount of stress in their jobs. Nonetheless, we must recognize that certain events, even in high-stress professions, may rise to the level of abnormal working conditions. Claimant did not simply witness death at a usual call involving a fire or a motor-vehicle crash. Claimant was actively involved in attempting to resuscitate two separate unresponsive babies and witnessing each of their deaths. We cannot agree that Claimant's experience in this regard was a "normal" or "expected" consequence of being a firefighter. Indeed, in Claimant's 20 years' experience in firefighting service before the first event, Claimant had never before had to perform CPR on an infant. There is no evidence in the record that suggests firefighters in [this municipality] or even in [this state] routinely or normally perform CPR on infant children or witness the deaths of infant children. Furthermore, it is noteworthy that, of the three instances in which Employer called upon the county's Critical Incident Stress Decreasement Team between 2018 and 2022, two of those calls were in response to these two incidents involving Claimant and the infants. Certainly, this highlights both the rarity of these events and the potential for substantial psychological impact to the participants, which is further magnified by the fact that the same person, Claimant, administered CPR on infants on each occasion.

Series of court opinions:

  • On a road with one lane in each direction, a posted speed limit of 55 mi/h (90 km/h), an "extremely wide" shoulder, and heavy motor-vehicle traffic, a bicyclist decides to ride at 15 mi/h (25 km/h) in the middle of the lane. A police officer gives him a ticket for obstructing traffic. At trial, the bicyclist boldly asserts that he had "no legal obligation" to avoid obstructing traffic, and claims that the shoulder was unsafe. The trial judge disagrees, finds him guilty, and imposes a fine of 25 dollars. The appeals panel affirms.

  • The state supreme court vacates and remands. The lower courts have been using a standard under which a bicyclist who is obstructing motor traffic always is required to get out of the way. However, when compared with the statute, which requires that bicyclists "use reasonable efforts so as not to impede the normal and reasonable movement of traffic", this standard is overly rigid. Instead, whether it is reasonable for a bicyclist to temporarily move to the shoulder (rather than, e. g., merely moving to the right edge of the lane) is fact-specific and must be determined on a case-by-case basis. But a bicyclist does have a duty to make a "serious, fair attempt" to avoid obstructing motor-vehicle traffic. (Two of the seven justices dissent. They think that the majority's new standard is too vague to give to bicyclists reasonable notice of what specific activity is lawbreaking, so in practice bicyclists will move to the shoulder in all circumstances, just as under the previous standard, due to fear of prosecution.)

  • On remand, the appeals panel affirms again. The police officer's dashcam video clearly shows: (1) the shoulder was perfectly safe; and (2) the bicyclist did not even once look backward at the cars whose passage he was obstructing, from which behavior the panel can infer that the bicyclist had no interest in making the "reasonable efforts" or "serious, fair attempt" to avoid obstruction that the law requires.

Love these posts, thank you

I now work in a legal-adjacent field and it's so interesting seeing how courts think.

I'm surprised that "abnormality" is a prerequisite for getting worker's compensation. Accepting for the sake of argument that PTSD is real, this is a real instance of PTSD, and it really prevents him from continuing in the same line of work, should "all firefighters experience this, and usually it does not result in them quitting with PTSD" be a sufficient argument to deny compensation? Does that mean that in cases like those radioactive watch face painters, where everyone in a line of work was exposed to a perhaps underappreciated probabilistic risk by convention, those who did get struck by it (the people who got cancer) have no claim to compensation?

to a perhaps underappreciated probabilistic risk

I think this is essentially pointing at the same thing the abnormality is. If you go into a dangerous job with full disclosure and knowledge that it's dangerous, you don't get special compensation because presumably you can ask for an appropriate risk-sensitive amount of compensation up front. If something extreme and unexpected happens, then presumably your original deal you signed was unfair. Underappreciated risks like radioactive watches or infant CPR deaths are the same general category of "did not really expect this or fully understand the risks"

That's not how the worker's compensation system is set up. As @ToaKraka notes below, the abnormality requirement only applies to psychological injuries, not physical injuries. As far as physical injuries are concerned, any injury that is work-related is eligible for compensation, and most of the litigation surrounding claims is question of either whether the claimant is too injured to do his job or whether the injury is actually work-related. If you wrench your knee climbing into the cab of the truck you drive for work, that counts. If you work with dangerous chemicals and are permanently disabled due to an explosion, it counts. If the workplace was seriously negligent, it counts. If it was an unpreventable accident, it counts. If the worker was injured because he failed to take required safety precautions, it still counts.

The idea behind the system is that traditionally, people injured on the job would have to sue their employers for lost wages, and the amount of time it takes suits to go through the courts meant that they could experience significant financial hardship even if their suits were successful. By eliminating the requirement of proving fault claims can be adjudicated in a matter of weeks (and subject to appeal if necessary) and claimants can receive benefits while they're actually out of work. The employer pays into the system like insurance.

The tradeoff is that this is the employer's liability is limited to what is available to the employee through the system. So if you're in an accident where the employer is seriously negligent (e.g. there's an explosion that makes the news and was caused by terrible safety practices) you won't get a multimillion dollar lawsuit but the relatively meager award based on a percentage of your average wage. The caveat here is that this only prevents suits against employers, so if you're injured on the job due to an accident caused by a contractor, you can still sue the contractor, or if you work for a contractor working at a steel mill and a mill employee does something stupid you can still sue the mill. The added requirements for psychological injuries is to prevent people from saying that they're job is too stressful so you should pay them not to work.

Should "all firefighters experience this, and usually it does not result in their quitting with PTSD" be a sufficient argument to deny compensation?

According to the state supreme court:

Abandoning the distinction between normal and abnormal working conditions would eliminate the element of causation. It would destroy the fundamental principle underlying the scheme of the Workers' Compensation Act—that, in order to be compensable, an injury must be work-related. Otherwise, a claimant would have to establish only that the employee suffered from a mental illness while employed and that the illness was a condition created or aggravated by that employee's perception of the conditions of his employment. That would reduce workers' compensation benefits to nothing more than a disability or death benefit payable only because of the employee status of the claimant—and not because the injury was caused by his employment.

There is a degree of uncertainty inherent in any employment situation, as in life itself, such that an employee’s individual, subjective reaction to ordinary vicissitudes is not the type of condition which the legislature intended to require compensation for because it is not, in the common understanding, an injury.

Does that mean that, in cases like those radioactive watch face painters, where everyone in a line of work was exposed to a perhaps underappreciated probabilistic risk by convention, those who did get struck by it (the people who got cancer) have no claim to compensation?

This standard is applicable only to psychological injuries, not to physical injuries.

What is this place?

This website is a place for people who want to move past shady thinking and test their ideas in a court of people who don't all share the same biases. Our goal is to optimize for light, not heat; this is a group effort, and all commentators are asked to do their part.

The weekly Culture War threads host the most controversial topics and are the most visible aspect of The Motte. However, many other topics are appropriate here. We encourage people to post anything related to science, politics, or philosophy; if in doubt, post!

Check out The Vault for an archive of old quality posts. You are encouraged to crosspost these elsewhere.


Why are you called The Motte?

A motte is a stone keep on a raised earthwork common in early medieval fortifications. More pertinently, it's an element in a rhetorical move called a "Motte-and-Bailey", originally identified by philosopher Nicholas Shackel. It describes the tendency in discourse for people to move from a controversial but high value claim to a defensible but less exciting one upon any resistance to the former. He likens this to the medieval fortification, where a desirable land (the bailey) is abandoned when in danger for the more easily defended motte. In Shackel's words, "The Motte represents the defensible but undesired propositions to which one retreats when hard pressed."

On The Motte, always attempt to remain inside your defensible territory, even if you are not being pressed.


New post guidelines

If you're posting something that isn't related to the culture war, we encourage you to post a thread for it. A submission statement is highly appreciated, but isn't necessary for text posts or links to largely-text posts such as blogs or news articles; if we're unsure of the value of your post, we might remove it until you add a submission statement. A submission statement is required for non-text sources (videos, podcasts, images).

Culture war posts go in the culture war thread; all links must either include a submission statement or significant commentary. Bare links without those will be removed.

If in doubt, please post it!


Rules


Recommended Posts And Communities

Recommended Realtime Chats