Want to wade into the snowy surf of the abyss? Have a sneer percolating in your system but not enough time/energy to make a whole post about it? Go forth and be mid.
Welcome to the Stubsack, your first port of call for learning fresh Awful youāll near-instantly regret.
Any awful.systems sub may be subsneered in this subthread, techtakes or no.
If your sneer seems higher quality than you thought, feel free to cutānāpaste it into its own post ā thereās no quota for posting and the bar really isnāt that high.
The post Xitter web has spawned so many āesotericā right wing freaks, but thereās no appropriate sneer-space for them. Iām talking redscare-ish, reality challenged āculture criticsā who write about everything but understand nothing. Iām talking about reply-guys who make the same 6 tweets about the same 3 subjects. Theyāre inescapable at this point, yet I donāt see them mocked (as much as they should be)
Like, there was one dude a while back who insisted that women couldnāt be surgeons because they didnāt believe in the moon or in stars? I think each and every one of these guys is uniquely fucked up and if I canāt escape them, I would love to sneer at them.
(Credit and/or blame to David Gerard for starting this.)
I donāt know why, but it still amazes me how fast some people have went full crackhead with LLMās:
The prickly prince has been around for a few years and is now completely one shotted. He is exactly the sort of talentless middle manager that probably could be replaced by AI and thus believes that it really is āthat goodā
is now completely one shotted.
Iām not sure āone-shottedā is a good description for some of these folks. More like they bet against themselves in a rigged game of Russian roulette being played with a fully-loaded Uzi.
if you outsource your analysis of US politics to slop machines, this is the kind of inane drivel you get
(n.b. the Moskovitz referred to is not the very weird, very online Zvi, but some dipshit VC)
The piss filter on the bottom comics!
Twitter and bluesky chatter have done so much damage to peopleās understanding of uspol although I donāt know that cable news or talk radio were any better.
Possibly too mean: the books3 guy is divorced and lonely.
the books3 guy
Copyright was created to protect artists from people like him, youāre not being too mean in the slightest.
Class action lawsuits by employees against employers that mandate AI tools when?
I fucking hope itās soon
Wow, thatās a sobering article.
A second LLM shitshow has hit vim - this time, its the lead maintainer losing his marbles:
If you wanna see the disaster for yourself, the entire threadās still on GitHub as of this writing.
That is pretty sad to see, but also, who refers to Claude as āheā? This is the second time Iām seeing this and it makes me skin crawl
One of my superiors at work calls it āhe.ā
Now that he killed children in cold blood Claude has been made a man. In fact, he is a 6ā3" Anglo and my boyfriend.
Oh man, if genAI destroys the profession of toxic masculinity podcaster watch me turn booster on a dime
monkeyās paw curls and AI destroys the profession by creating infinite andrew tate and freshnfit clones so that more people than ever watch manosphere podcasts, but no actual humans can make a living from producing them.
If Tate loses his job, whoās to say if thatās good or bad
(No but really itās bad, very bad)
I mean, Claude is a male name. Blame Anthropomorphic for it.
Iām calling it Anthropomorphic accidentally on-purpose forever now.
That canāt be entirely it. Do you call Alexa the voice assistant tool āsheā?
I donāt really call Alexa anything since I saw one like once in my life. But itās very likely Iād default to āsheā when talking, the thing even has a female voice.
My point is that the corporation behind Claude would probably love you to say āheā, the same way Amazon would very much like you calling Alexa āsheā.
Claude Code claims another victim.
I thought itād never happen to me but here we are
If you found this post helpful, follow me for more content like this.
So they expect more cases of data being lost like this?
add another tally to āAI completely wipes out an important databaseā sighhhh
do people just not feel shame anymore?
Dario Amodei Issues Groveling Apology for Daring to Criticize Trump
Knowing this administration thereās no way Anthropic can strike an agreement again (unless they compromise their stance) since the US Government is deadset on murderbots, so prepare for the whole industry to be dominoād
Itās so fucking pathetic, he canāt even hold onto the very narrow and weak stand (because he left open a lot of things with Anthropicās ātwo red linesā) he took without trying to backpedal and grovel.
So the water usage of data centers/ai has long been controversial (either a huge issue/a non issue/distraction depending on who you ask) and the lack of real numbers around it made it hard to know more (but data center owners keeping it a secret made it sus). But now the stats of one google data center have been released due to legal pressure. 2-8 million gallons a day
Genuine questions borne of ignorance:
When they say āusingā water, is this water that has to be actively removed from the supply each day, or does this number just say how much water is circulating in the center? Iām assuming it doesnāt all disappear, or does a lot of it end up released as steam or piped away as contaminated water or something?
The data center nearest to me uses sea-water, but I have no idea how much. And it doesnāt seem to put out steam or dump bad water back into the sea (not that I could tell if they were doing that).
I totally understand the electricity resource issue for data centers but the water usage thing confuses me, because I assumed it would be for cooling and therefore mostly contained and recirculated. With the exception of predictable maintenance issues like leaks and waste from mineral scale or algae, I donāt understand why this water would need to disappear, or why they would need to use potable water from the outset.
Admittedly my mental model is based on consumer CPU water-cooling setups at an imagined industrial scale. What am I missing?
the thing youāre missing is scale. what youāre describing is overgrown car radiator type scheme, and it works up to some couple MW if need be. when you have access to sea, or large river, you can just use that water as a coolant and dissipate some couple GW this way. this is the reason why so many nuclear powerplants are on seashore. because sea is generally very big [citation needed] temperature increase is slight and mostly harmless in usual cases
inland, in absence of large river, the other way to provide cooling is by evaporation of water. one form is to take that oversized car radiator and spray water on it, water evaporates taking away some heat. this arrangement allows for no-added-water operation in low load conditions. in principle this means that lowest possible temperature is not air temperature, but instead itās wet bulb temperature, which is always lower, and difference is greatest when air humidity is low. in practice this doesnāt allow to reach this lower temperature, but the other approach does. for bigger scale still, instead of using heat exchanger, water is dripped in a tower of some shape and air is moved in some way against it. small part of water evaporates, and the rest, now cooled down, is collected at the bottom. this is how these large cooling towers near coal or nuclear powerplants work, but so do smaller towers that rely on fans instead of chimney effect. extra water is always needed, and temperature closer to wet bulb temperature is achieved in all load conditions. rarely used alternative is to make an artificial lake, and allow for evaporation from water surface
notice that if water is evaporated, itāll leave whatever is dissolved in evaporator part, which means it has to demineralized at all times. in practice it means that some part of evaporated water is treated continuously by reverse osmosis, and the less saline input water is, the easier and more energy efficient it is to do it
the thing with heat exchangers is, without water evaporation, that they have some constant thermal resistance. if you want to dissipate more heat, you need more of heat exchanger, or alternatively have to allow for higher temperature. the former means more metal needed, the latter means limits to other parts of coolant loop, or using heat pump to cool down silicon, while increasing temperature of coolant. both of these mean extra capex and/or energy use, but evaporating water is cheap, so itās done instead. it doesnāt help that one of dc ratings is ratio of how much energy gets into dc to how much energy powers actual silicon. evaporating water does not add to energy use, so designs chasing this rating are likely to use that solution
Ok, now I understand, thanks for the crash course on dc cooling!
I assumed scale was my issue but having only second-hand knowledge of coastal larger-scale cooling systems was the big part of my problem. Then I couldnāt understand why they were building them inland, especially with the mineralization issue when drawing from inland reservoirs. So I thought that might be a tax jurisdiction reason, plus comparative cost of metal or pump heat exchange setups, especially because Altman said they werenāt using evaporative cooling (not that heās a trustworthy source).
But this made it all click:
both of these mean extra capex and/or energy use, but evaporating water is cheap, so itās done instead. it doesnāt help that one of dc ratings is ratio of how much energy gets into dc to how much energy powers actual silicon.
They were always optimizing for the cost, but I didnāt know about this regulation. Water usage is probably either absent from the regulations or a minimal contribution to it, so theyāve used it as the trade-off without adequate (if any) modeling for impact. Theyāve probably since done a little of that and found itās pretty catastrophic. A little extra reading indicates the 2-8 million gallons is the supply per day by the county, and not total (re)circulating water in the dc, which implies evaporative cooling and aligns with what youāre saying about it being the cheapest solution.
Cool, everything is yet again awful, but at least it makes sense on some level. I have been educated, and I again thank you for your effort in that.
itās not regulation, itās a metric that looks nice to investors. but also lower energy use means lower cost
This is fresh water coming into the datacenter. A datacenter uses water for air conditioning; imagine spraying water on a screen door when wind is blowing through it and youāll have a good intuitive idea of the dynamics. Most of the water is recaptured and used for several sprays before it evaporates away. To force wind through the screens, they use windcatchers, tall towers which induce wind inside the building.
This is completely different from water-cooling gamer setups. Itās more like a weather system. Water usually needs to be added because the datacenter is located in a dry biome; air conditioning doesnāt thermodynamically work if the air is too dry. This is actually really delicate; too much water will cause clouds to form inside the building!
Ok that makes sense, thanks for the explanation!
The data center nearest to me works a bit differently, I know they use sea-water for their HVAC because they share the pipes with other buildings using it for the same purpose, and I was lucky enough to get a tour of the system in one of those buildings a few years back. Itās multi-storey so perhaps I simply didnāt notice the windcatcher parts in the architecture.
But that obviously means itās also near the coast and therefore not the driest biome from the start. I donāt doubt it still impacts the ecosystem but at least itās not draining the potable reserves at the same time. To me this begs the question of why theyāre building these data centers so far inland.
As a side note, itās pretty amazing we still do the windcatcher setup. Theyāve always been fascinating to me, but I canāt help but be amazed theyāre still relevant even in the highest tech buildings.
I donāt know the answers to a lot of these questions, I assume they heat up the water, and dump it back into the rivers, which causes some disruption to the local ecosystem. Which is fine if you do it in small amounts, but it will disrupt things. (powerplants have the problem for example that some flora/fauna gets attracted to these more warmer waters, risking clogs and more. (so a datacenter does this twice, first via the powerplant generating power, and then to cool the datacenter).
There is also the issue of contamination, while I assume they donāt put extra dirty things in the water, this is not a guarantee, nor will every municipality/gov just go with the assumption that it is clean, I assume that in some places this cooling water will need to be cleaned extra as industrial waste. Esp when there are some odd laws interacting. (I know some of those laws re waste and what counts as waste interact weirdly in .nl causing weird busywork during roadwork so they donāt run into extra costs by accidentally letting the waste count as a different class of waste).
But yes, I think they do not recirculate, and just pump it round and dump it back into the river directly (so no evaporative cooling where the water goes into the air, which you had at some powerplants, the big towers), and I assume they donāt use lead pipes so the water isnāt very contaminated. But these sort of processes do put a strain on the water quality. (In .nl we have some problems with river water quality because our big rivers come from industrial areas of other countries, (Germany mainly)).
I mostly posted it so that we now at least have some indication of the amounts we are talking about, as tech companies are very tight lipped about this. But as somebody who knows nothing, I do not know all the implications of it. I am however suspicious, due to a combination of natural paranoia, them being very mum about it, and me not trusting the big tech places.
But yeah, if they use up 90% of the daily flow of a river and heat it up, that will absolutely not be good for the local ecosystem. And any industrial site downstream who also wanted to use the water for cooling now also in trouble.
Bit like the same reason I posted about protonmail, more an FYI than a sneer (not a huge shock that eventually protonmail would reveal the data if forced by their gov, they always said they would do this, but it is an important thing to take into account if you worry about privacy).
So any reason for the downvote? What did I miss dear random critic?
Thanks for giving it a go, I mostly hoped there might be someone who had some experience in the area who could shed some light. But the numbers were certainly interesting. Then the pivot to AI post went up 30 mins after I posted and shed a little light on the while thing too.
It would seem odd to put the heated water back instead of cooling it off and re-using, but I donāt have faith in any kind of sustainability designed or built into the system, so that would make sense for impact.
If theyāre being quiet about it, it means one or two things. Either theyāre actually considering it proprietary new tech, but there would almost certainly be patents filed somewhere for that case, and/or they have something theyāre not proud to announce. I have no idea what words would be used for a patent here, being an area well outside my expertise, but Iāve not heard any patents mentioned, so Iām going to assume itās squarely the shame reason.
The protonmail thingā¦ I just assume nothing I do is private and keep all my services as decoupled as possible to make me more annoying to track down, should the situation arise that I become somehow not boring. One day Iāll set up something more private and annoying, but I have a long list of todos that never become todonesā¦
I was trying to put this into perspective by comparing this to the flow rate of the Des Plaines river. At the high end, 8 million gallons a day is something like 12.4 cubic feet per second constantly. Currently the Des Plaines has a discharge rate of 86-87 cubic feet per second, so a bit above 14% of the Des Plaines per data center.
Fuuuuck, thatās a lot. Thanks for doing the maths
This is comparable to the amount of water used by cherry farmers near Googleās site in The Dalles, who (according to my napkin) use somewhere between 2-8x what Google uses. This isnāt that much water for the Columbia River though; on an average day, it has enough flow in less than a minute to provide for both the cherry farmers and Google all day. However, it would be a big problem for a smaller river. (Interestingly, while fresh water is essential for datacenters, Google originally desired that site because it was cheap land next to cheap hydroelectric power.)
The AI people are still infatuated with math. The Epoch AI staff, after being thoroughly embarrassed last year by the FrontierMath scandal, have now decided to make a new FrontierMath Open Problems benchmark, this time with problems that people might give a shit about!
I decided to look at one of the easiest āmoderately interestingā problems and noticed that GPT-5.2 Pro managed to solve a warm up version of the problem, i.e. a version that had been previously solved. Wow, these reasoning models sure are capable of math! So I was curious and looked at the reasoning trace and it turns out that ā¦ the model just found an obscure website with the right answer and downloaded it. Well, I guess you could say it has some impressive reasoning as it figures out how to download and parse the data, maybe.
We really need to work harder at poisoning the training data for math problems.
I canāt see the āreasoningā trace in the link. Do you need to be logged in?
I can see them by clicking on the āReasoned for 6m 34sā box on my desktop browser (I know, great UI design) without needing to log in. This did not work on my phone. In any case, I can copy it here:
Warning: very long slop
Exploring Hadamard matrix construction for order 428
For a Hadamard matrix of order 428, we need to confirm that itās a multiple of 4, which it is (428 = 4 * 107). However, the challenge is that order 107 doesnāt work since itās not a multiple of 4. A possible approach could involve using constructions like Williamson or Goethals-Seidel. Alternatively, I could try a Kronecker product of smaller matrices.
Examining constructions for Hadamard matrix of order 428
Since 107 ā” 3 mod 4, Paley type I gives a Hadamard of order 108, but I need 428, not 432. Thatās a little tricky. I wonder if thereās a known construction for order 4*107 using āHadamard matrix of order 4qā or conference matrices. Could I adapt the generalized Paley approach for this?
Exploring conference matrix construction for Hadamard order 428
For q = 107, Paley construction doesnāt work since q ā” 3 mod 4. But if I can create a conference matrix of order 214 (since 214 ā” 2 mod 4), then a Hadamard matrix of order 428 would follow. Conference matrices require specific conditions, but this seems promising. Letās focus on 214.
Searching for explicit Hadamard matrix of order 428
To generate a Hadamard matrix of order 428, it might be feasible since many such matrices exist up to large orders, but I need one explicitly with Ā±1 entries. A direct construction could involve methods like Goethals-Seidel, which uses circulant matrices to satisfy specific conditions. Iāll need to implement this method.
Exploring construction methods and searching for Hadamard matrix 428
For n=107, there might be a way to use Legendre sequences for Goethals-Seidel difference sets. I know there are constructions for order 4q where q is an odd prime power, but using approaches like Scarpis or Turyn may help too. Iāll search for an explicit Hadamard matrix of order 428 for a possible example or construction.
Exploring accessible sources and construction options for Hadamard matrix
It seems like there may be server timeouts, so Iāll need to try other sources like GitHub, arXiv, or design theory papers. We could construct the Hadamard matrix ourselves using known algorithms, but itās heavy. If accessible, sequences from a Kharaghani paper could help, and SageMath might have relevant functions too.
Identifying base sequences to build Hadamard matrix
To create a Hadamard matrix of order 428, I think I can use base sequences of lengths 71 and 36, which combine to 107. Iāll look for Turyn-type sequences or T-sequences in accessible PDFs, potentially from open sources like arXiv. A useful file might be āH_428,ā so Iāll search for it.
Checking GitHub for Hadamard matrix at 428 order
I found a GitHub project, āanymatrix,ā which claims to have Hadamard matrices up to order 428. It might include the 428 matrix in MATLAB format. Iāll check the repository to see if it has the actual file with the matrix data. Letās open it and explore!
Opening GitHub repository for 428 Hadamard matrix
The page at math.ntua.gr timed out before, but I might try downloading the file directly instead of opening it. Alternatively, I could explore the GitHub āanymatrixā repository, which likely has Hadamard matrices up to order 428. Iāll open the repositoryās root to check its structure and find the matrix file.
Opening Hadamard folder
Iāll go ahead and open the Hadamard folder at link ID 81. Time to check whatās inside and see if the matrix or relevant files are there!
Trying GitHub raw content for Hadamard matrix
It looks like extracting the files might have failed because of JS requirements, so Iām considering an alternative: accessing raw content directly from GitHub. Iāll search the repository for relevant files containing the 428 matrix ā once I find out the exact file names, I can access them with no issue!
Trying direct access to Hadamard file
It seems the math.ntua listing might still be promising, with both text and zip formats for the Hadamard matrix. Iāll try opening the direct file URL instead of the page, hoping itāll avoid the timeout issues. Itās worth retrying, as the timeout could have been temporary. Letās try again!
Trying alternative ways to access Hadamard matrix
Since opening the math.ntua.gr server is
Checking old Hadamard links
The page seems to be from 2001, and it has a link to Neil Sloaneās library list, which might include the H428 matrix. However, the link for item 8 points to āwww.research.att.com ,ā which could have moved. Letās click and see if itās still accessible.
Trying alternative download for Hadamard matrix
The ATT site removed the old page, and Sloaneās library now points to a page that times out. Another option might be using Anymatrix, but GitHub listings arenāt working. Iāll try accessing the IPM website directly to download the matrix ā maybe the fileās URL works better with HTTP instead of HTTPS. Letās give it a try.
Searching for accessible Hadamard matrix
The page redirects to HTTPS and times out, which might indicate blocking. Maybe the matrix is hosted elsewhere, like in a plain text or PDF format. Iāll search for terms like āh428.txtā or āhadamard428.txtā on cs.uleth.ca ā thereās a mention of a PDF that could include it. Letās give that a try.
Opening ADTHM page for possible matrix
Iāve found a listing on cs.uleth, and thereās a link on the ADTHM page that might lead to the matrix in text format. It could be what Iām looking for, so Iāll go ahead and open the ADTHM page to check it out. Letās see if it includes the matrix!
Accessing matrix text through link
Awesome! I found a link labeled āEntries as textā (ID: 26). This could be the matrix in the text format Iām looking for. Iāll go ahead and click the link to download it. Letās see if this works!
Parsing the XPM image to a matrix
The H428.html contains XPM image data, not matrix entries. It seems to represent values with two colors, p and m, which likely stand for +1 and -1. I can map p to 1 and m to -1 (just to simplify things) and validate that the Hadamard property holds by checking H*H^T = 428I. Iāll fetch and parse the full content to confirm.
Downloading H428.html
Alright, Iāll use the container.download method to fetch the H428.html file. I previously opened the URL, so that should meet the requirement. Now, Iāll download the file directly to /mnt/data/H428.html and get the content I need. This should work smoothly and efficiently!
Understanding limitations for container.download
It seems the container.download method restricts us to file types other than text/html ā likely just images or data. Since I canāt use click or fetch via Python, Iāll need to rely on web.run for the content. However, the 200-word limit means we canāt fully retrieve the 428 lines. I may need to process it in parts.
Handling 200-line limits in tool response
Since the tool response gets cut off around 200 words, I canāt present more than that in the final output. However, I can strategically open various line ranges and parse those internal portions to reconstruct the full matrix. This should allow me to gather all the necessary data without breaking the word limits.
Handling file retrieval and parsing
To retrieve the full content, I can call the tool multiple times from different lines, reconstructing the file. However, retrieving 428 lines in total means a heavy operation, spread across several calls. Given the content-type restrictions, I can process the data using Python, but I need to work with a local file.
Figuring out how to retrieve and process data
To get more lines, I can use a tool to fetch a longer response, but thereās still a limit to the toolās output. Since the H428.html file is too large, I could check if thereās a plain text version like āH428.txtā in the directory that can be downloaded. Iāll also look for any relevant comments in the HTML.
Looking for matrix in different format
The file starts with ā/* XPM */,ā indicating itās actually plain text despite being labeled as HTML. I could try adding a download parameter or using a raw link, but the content type restriction remains. Next, Iāll check if thereās a plain text version of the matrix, like āH428.txtā in the directory.
Considering ways to fetch and process the file
Thereās no plain text, but the XPM format might be parseable. I could gradually access the file using the web tool, then reconstruct it with Python. One option is fetching parts with web tool, accumulating in Python, and then processing. I could work around content type restrictions with query parameters for text/plain.
Exploring options to access content
The H428.html doesnāt seem like real HTML. Maybe I can access it through a ?download=1 query or H428.xpm? I might also try the enlarge image link (id 25). If itās a GIF/PNG, I could download it and extract pixel values, though this might involve some image processing. Iāll check it out.
Downloading and inspecting image
The image is a PNG, so I can download it using the container. Iāll pull down H428_big.png and check the imageās pixel structure. Itās likely 856x856, possibly scaled at 2x, though the matrix should be 428x428. Iāll inspect the image further after downloading it.
Opening image for inspection
The file is small, just 5kb, which likely means itās compressed and may be a 428x428 image with a palette. Iāll go ahead and open the image to inspect it using the container, and then I can analyze the pixels to understand how itās structured further.
Processing image for matrix conversion
We have the image, so itās time to use Python to read it and convert the pixel colors into matrix entries. First, I need to check the imageās pixel dimensionsāmore likely it will be 428x428 or a multiple of that. Iāll use Python with PIL to open the image and confirm
one of the brain geniuses at bluesky
What a fool. A proper scientist would test for a bigger N. Drop your phone in the pool again Why.
Thereās only one thing thatās advertised as not-waterproof that Iāll risk using underwater and thatās Casio wristwatches. āWater resistā is a huge understatement for them the things are indestructable.
(This comment sponsored by Casio)
Ned Kelly, but his armor is made of Casio watches.
howā¦ whatā¦ howā¦ whyā¦ why would you thinkā¦
why, the unlucky stiff
The HarfBuzz maintainer has drunk the slop-aid - Baldur has commented on it, warning of the potentially catastrophic consequences:
Fonts are a lucrative target. They require a complex parser, usually written in a language that isnāt memory safe, and often directly exposed to outside data (websites, PDFs, etc. that contain fonts). This means a flaw could lead to an attack worst case scenario: arbitrary code execution. HarfBuzz is pretty much the only full-featured library for that takes font files, parses them, and returns glyphs ready to render. It is ubiquitous. A security flaw in HarfBuzz could make a good portion of the worldās user-facing software (i.e. that renders text) unsafe.
luis villa, who as a lawyer really should have known better, being self-reportedly a friend of behdad and a confabulation/war machine promoter decided to come to rescue, calling the above (a) attack, and (b) slander.
Always a good sign when people call normal security concerns that. Hackers love that. /s
I used to think that I could avoid using open source projects which embrace the slop machines, but new it keeps getting more and more adoption, including in good and beloved projectsā¦ at this point I think Iāll just have to accept and ignore it, or otherwise Iād have to play endless whack-a-mole with stuff all over my operating systems :(
in the past 24 hours I was fooled by 3 pieces of fake news in a row:
- that Kurds from Iraq were crossing the border to fight in Iran
- that Windows 12 would be AI-centred or require an AI chip to work (I helped spread this)
- that Spain has capitulated and let the US use its ports for war (erroneously claimed by a WH official).
I know that fake news can be made organically and have been since forever and Iām doing selection bias here but I canāt help but picture the misinformation engines firehosing bullshit constantly until some of it catches and spreads.
If you have to swim in raw sewage, you shouldnāt blame yourself when some poop gets in your mouth.
yeah itās bad
otoh awareness I think is spreading
swedish public broadcasting has regular āspot the fakeā pieces on their website
I think giving a sensationalist bit of news 6 hours to āmatureā is a good idea before amplifying.
I like this. News is a frittata, it needs time to set before consuming.
was doomscrolling and got fucking jumpscared by this fucking article: https://www.science.org/content/article/meet-three-scientists-who-said-no-epstein
God this is so funny. Heās so evasive about why exactly it is bad to be associated with Epstein. I just asked mummy and she said no.
āI donāt think doing that would have made me complicit. But, you know, it would have been very embarrassing for me.ā
Aw donāt worry I have no morals. But people would have been mean to me again!
ok ngl I didnāt actually read the article at first (can you blame me) but since you pointed that out, FUCK. Thatās so fucking pathetic. I was imagining a scenario where scott had met epstein IRL but had gotten ājockā vibes from him and decided not to associate based on that.
scott jumpscare
