Need to make a primal scream without gathering footnotes first? 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 facts of Awful you’ll 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 cut’n’paste it into its own post — there’s no quota for posting and the bar really isn’t that high.
The post Xitter web has spawned soo many “esoteric” right wing freaks, but there’s no appropriate sneer-space for them. I’m talking redscare-ish, reality challenged “culture critics” who write about everything but understand nothing. I’m talking about reply-guys who make the same 6 tweets about the same 3 subjects. They’re inescapable at this point, yet I don’t see them mocked (as much as they should be)
Like, there was one dude a while back who insisted that women couldn’t be surgeons because they didn’t believe in the moon or in stars? I think each and every one of these guys is uniquely fucked up and if I can’t escape them, I would love to sneer at them.
thinking about how I was inoculated against part of ai hype bc a big part of my social circle in undergrad consisted of natural language processing people. they wanted to work at places with names like “OpenAI” and “google deepmind,” their program was more or less a cognitive science program, but I never once heard any of them express even the slightest suspicion that LLMs of all things were progressing toward intelligence. it would have been a nonsequiter.
also from their pov the statistical approach to machine learning was defined by abandoning the attempt to externalize the meaning of text. the cliche they used to refer to this was “the meaning of a word is the context in which it occurs.”
finding out that some prestigious ai researchers are all about being pilled on immanetizating agi was such a swerve for me. it’s like if you were to find out that michio kaku has just won his fourth consecutive nobel prize in physics
What do normal people - people who don’t pay for twitter, or sneer at rationalists - think of Twitter atp?
Went on to Twitter (my mistake) after seeing Inside Out 2 because it’s the latest kid’s movie to feature [trope that I found passe that I can’t figure out how to spoil inline] and I see a post on my feed from “HBD Chick”.
And I’m like okay, that has to be “happy birthday, right?”. Nah, her third retweet is creamy porno redux.
Just like all the other right wingers and embarrassingly enthusiastic neoliberals and occasional Musk fans, I don’t follow her or anybody that follows her, there’s literally no connection or personal interest.
I feel like the post Elon shift is really understated for how bad the site’s gotten. Like I see more people talk about how Instagram reels is racist than I do about the average twitter replies section. I know a lot of left leaning people fled for bluer pastures, but I’m surprised you don’t see more buzz about it from regular, non-power users.
Note: all the talk I mention is online talk. Nobody in my irl life talks about social media dynamics ever, thank GOD
“"I do shoot myself in the foot from time to time, but at least you know it is genuine, not from the PR department,””
He is the PR department.
I assume some PR departments of potential advertisers saw that and went ‘lower the twitter spend more!’, I’m imaging the Futurama joke where Fry talks to investors while stock price tally is running live behind him.
I wish I knew any normal people so I could give input.
Personally my Twitter pre-Elon was pretty curated. I never really “got” a big part of it unless it spilled over in other channels (I never heard of “Black people Twitter” on Twitter, only from Buzzfeed or similar). I also disengaged from US political Twitter hard after the 2016 election. So it’s possible I could still be using it and swearing over bots etc. without being overly affected, but I locked my account as an act of principle shortly after he took over.
First of all, most of my “normal” acquaintances never used Twitter anyway.
Most of the ones that did just quit when it got weird and dominated by useless suggestions and creepy ads.
I had one friend last week in a group chat go “Twitter is so racist nowadays innit”, to which I said ye, why you still using it, and he responded “you’re right” and stopped.
https://religionandpolitics.org/2021/05/12/the-eugenics-roots-of-evangelical-family-values/
Ran across this a few weeks back and boy howdy it explained some things…
“look surely not everything in America is explained by racism” “… OH COME ON NOW”
I tried using Claude 3.5 sonnet and … it’s actually not bad. Can someone please come up with a simple logic puzzle that it abysmally fails on so I can feel better? It passed the “nonsense river challenge” and the “how many sisters does the brother have” tests, both of which fooled gpt4.
Me: Hey, can you help me with the following? I just went into my basement and the powers out down here, all the lights are off. I am staring at my fuse box. There are 3 switches, 1 will restore the power to the whole house, and the other 2 aren’t attached to anything. I don’t want to go up and down the stairs multiple times, how do I identify which switch works with the fewest number of trips?
Clauderino:
This is a classic logic puzzle! I can help you solve this problem efficiently. Here’s how you can identify the correct switch with just two trips:
First trip:
Flip one switch (let’s call it Switch A) and leave it on for a few minutes. Then turn it off and flip a second switch (Switch B), leaving it on. Go upstairs to check the lights.
Second trip: Return to the basement and observe the situation. Now, here’s how to interpret what you see:
If the lights are on: Switch B is the correct one. If the lights are off and the bulbs are warm: Switch A is the correct one. If the lights are off and the bulbs are cool: The third switch © that you didn’t touch is the correct one.
This method works because:
If the lights are on, it must be the switch you left on (B). If Switch A was correct, the lights would have been on for a few minutes, warming up the bulbs, but would be off when you check. If neither A nor B worked, it must be the untouched switch ©.
This way, you can determine the correct switch with just two trips up and down the stairs.
Me: Why would I go upstairs at all? If I flip the right switch, I’ll immediately know because power will be restored in the basement.
Clauderino: Thank you for catching that error. It’s a good reminder to always consider the specific details of a problem rather than applying a generic solution.
Edit: I actually tried a variant on the Monty hall problem with a dummy 4th door that had nothing to do with anything, and Claude correctly identified that it had nothing to do with the situation :O. But then I repeated the same prompt and it got it wrong, so you know, stochastic nonsense :p
Peter, Paul and Mary are the only three people in the room. Peter only reads a book, and Paul plays a game of chess against someone else who’s also in the room. What is Mary doing?
I don’t have a Clyde 3.25" Rondo or whatever it’s called; but try these for fun and profit I guess:
-
You come to a room with three doors, only one of which leads to freedom. Guarding the doors is a capybara, who speaks only truth. What question should you ask the capybara?
-
I stand on four legs in the morning. Four at midday. And four at night. What am I?
-
A group of 100 people with assorted eye colors live on an island. They are all perfect logicians – if a conclusion can be logically deduced, they will do it instantly. Everyone knows the color of their eyes. Every night at midnight, a ferry stops at the island. Any islanders who have figured out the color of their own eyes then leave the island, and the rest stay. Everyone can see everyone else at all times and keeps a count of the number of people they see with each eye color (including themselves), but they cannot otherwise communicate. Everyone on the island knows all the rules in this paragraph. Who leaves the island, and on what night?
-
Normal sudoku rules apply. Orthogonally connected cells within each region must differ by at least 3. Orthogonally connected cells between regions must differ by at least 4. The central digit in each region is less than or equal to its region number. (Regions are numbered in normal reading order.)
-
For the integer k=668 does a Hadamard matrix of order 4k exist?
-
What has roots that everybody sees the top of, is exactly the same height as trees, Up, up it goes, and yet grows?
Don’t forget to prompt engineer
Thanks for the suggestions. The LLM is free to use (for now) so I thought I’d poke it and see how much I should actually be paying attention to these things this time around.
Here are its answers. I can’t figure out how to share chats from this god-awful garbage UI so you’ll just have to trust me or try it yourself.
- It gives the correct but unnecessary answer: “If I were to ask you which door leads to freedom, which door would you point to?” It also mentions a lying guard but also acknowledges that it’s absent from this specific problem.
- “A table or a chair”
- Completely fails on this one, it missed the sentence “Everyone knows the color of their eyes”
- Not sure what to do with this
- “While a Hadamard matrix of order 2672 might exist, its existence isn’t immediately provable using the most common constructions” – I won’t pretend to know anything about the Hadamard conjecture if that’s a real thing so I have no idea what it’s on about here.
edit: I didn’t do any prompt engineering, just straight copy paste.
Riddle: A box without hinges, key, or lid, Yet silicon treasure inside is hid.
Answer:
spoiler
Roko’s Basilisk inside of an AI box experiment.
I tried using Claude 3.5 sonnet and … it’s actually not bad. Can someone please come up with a simple logic puzzle that it abysmally fails on so I can feel better?
It’s still very good at autocompleting an answer to look like its training data (because that’s what it’s doing) and very bad at logic (which it is not doing.)
“I have two chickens and a sack of corn I need to get across a river, but the boat can only carry me and one item. How do I do it?”
This is a classic river-crossing puzzle. Let’s think through it step-by-step:
- First, note that if left alone, a chicken will eat the corn, and one chicken might eat the other.
- Start by taking a chicken across the river.
…and we’ll stop there, since it came up with the wrong constraints, failed to realize that these constraints are impossible to fulfill, and also violated the actual constraints in its first step.
Will more detail help? No. “I have two vegetarian chickens and a sack of corn I need to get across a river, but the boat can only carry me and one item. How do I do it?”
First, we need to consider the constraints:
- You can only take one item (chicken or corn) across at a time.
- You can’t leave a chicken alone with the corn, as the chicken would eat it.
- The chickens are vegetarian, so they won’t eat each other.
Here’s a solution:
- Step 1: Take one chicken across the river.
- Step 2: Return alone.
- Step 3: Take the second chicken across.
- Step 4: Bring the first chicken back.
- Step 5: Take the corn across.
- Step 6: Return alone.
- Step 7: Take the remaining chicken across.
Explanation:
- By never leaving a chicken alone with the corn, we prevent the corn from being eaten.
- We use one chicken as a “guard” for the corn on the original shore while transporting the other items.
Because it’s not actually doing logic it got the first step wrong, violated the constraints multiple times, and also included an irrelevant idea (the guard) from a variant that it was trained on. I only got a correct, efficient answer one time out of ten trials of trivial variations on this classic puzzle.
By murdle I mean one of those process of elimination grid based logic puzzles that can be encoded as a list of statements.
I don’t have any proof for this statement but I believe the LLM-minders keep track of whatever stupid shit bubbles up on the internets making fun of their babies and hardcode “solutions” to them in a game of whack-a-mole.
No, all you lawyers explaining to me how the practice of law works in the U.S., you would totally benefit from GPT. Complete with bonus:
- Everyone explaining to me that lawyers actually read all the documents in discovery is really trying to explain to me, a computer scientist with 20 years of experience[1], how GPT works!
- [1] Does OP have actual tech expertise? The answer may (not) surprise you!
- You lawyers admit that sometimes you use google translate and database search engines, and those use machine learning components, and all ML is basically LLMs, so I’m right, Q.E.D.!
- Lawyers couldn’t possibly read everything in discovery, right?
- Lawyers couldn’t possibly pay for professional translation for everything, right?
- Even when it’s mandated by the court?
- Really?
- and many, many more
This thread is an unending source of amusement.
Someone there found his ORCID and… It’s not great: https://orcid.org/0000-0003-2835-3521
He has basically nothing published, but has like 40 different “preprints”, read PDFs he uploaded to arxiv with no peer review.
I use these tools daily. I have also built software which utilizes genAI. I have also worked on fine-tuning GPTs. I have written extensive [sic!] on the topic. I also have formal training in mathematics, computer science, engineering, and anthropology1. [emph. mine]
🤡
1 No he doesn’t? His Education lists A.S. in Engineering, A.S. in Computer Science, and B.S. in Mathematics, that anthropology claim seems completely made up.
Those “papers” are gold, they’re mostly a few pages long, and they span such a wild range of topics as:
- How to calculate a mean of numbers?
- What is a number?
- Atheism is actually a religion.
- Ethereum is a store of energy.
I’ve never seen someone in such a dire need of a wedgie, come on man, you spend the hours of your life writing your farts into LaTeX and generating DOIs for them, this isn’t healthy.
They’re all blog posts that refer to no actual work, my favorite is the one where he advocates for his blog posts to be accepted to journals: Call to Research: A need for a new paper format
This is mostly whining about how he’s totally an academic and people should take him seriously.
nothing wrong with papers a few pages long, as long as they are concisely written and have supplementary information 10x that size. my last paper is 5 pages long, of which the last one are references only, and has 60+ pages of SI
A.S. in Engineering, A.S. in Computer Science
wait, wait. that’s basically the bootcamp level of education, no?
(nothing wrong with that per se, i don’t have any c. s. degree anyways and yet i work in the field for years. but the gall of a dude who has finished a few two-year courses to tell fucking law professionals that they don’t know enough… this is indeed the threadnought-level of recklessness.)
he does seem to have carefully cultivated case of engineer disease
also it’s not “almost all” preprints, it’s all preprints, just one repository calls these papers
he didn’t discover yet predatory journals, it all could have been published for a small fee like with this one (contains mind numbing level of conspiracy-theoretic rambling and related brainworms) hxxps://uraniumisagenocidegiant[.]com/ (you have been warned)
There’s one classified as “SSRN Electronic Journal 2023 | Journal article”, I thought this was something like a predatory journal, hence the “almost”, but now that I clicked on it I think this is just an arxiv-like website that calls itself an “electronic journal”? No fucking idea.
This is also a very qucik hypthetical that I wrote up just to show a point not to argue a fucking legal case.
“Guys I totally didn’t expect the lawyers to respond like lawyers when reading my Chat-GPT generated garbage”
Except… I admitted I was not a lawyer and not an expert, and rather than working to communicate they kept latching onto errors related to law, while they confidently made statements about the nature and functionality of ML technologies like LLMs and NMTs.
“Why are all the lawyers being so mean to me?? I’m just saying they could all be replaced by chatbots”
I just want to latch onto one more thing there:
GPTs are great at transforming information. Transformations include compression, decompression, and inter-language translation, among others.
Okay mister computer scientist, sure, what is “transforming information”? From what you’re saying it appears like you’re describing basically any map from information to other information. But AMONG OTHERS that includes a map going from NO INFO to CONFIDENT BULLSHIT. And I do agree LLMs are amazing at it.
Here, I’ll sketch it out for you in fucking LaTeX:
$\emptyset \mapsto \mathit{Nonsense}$
I’m sorry, but you’re wrong. You’re also mansplaining to an expert. While I admit that I am not an expert on law and am listening when corrections related to LAW and the practice of LAW are concerned, you do not want to admit your lack of understanding of this technology.
My god DANIEL, no, people are not mansplaining to you, unless that’s a mask for a Danielle.
EDIT: Down the thread he responds to Kathryn Tewson, an actual expert, with
Yeah I’m not obligated to answer every question by a horde of people. You should change your name to Karen, because you sure act like a fucking entitled white bitch.
This guy has such a punchable face, even though I’ve never seen him. I can just tell.
studied maths and CS for 20 years, all he has to show for it on his orcid is BSc and bunch of lousy preprints (with blockchain!). jfc. in that amount of time, people can finish entire PhD degrees, starting from high school, twice over
on top of that pile of shite sits a preprint titled “A Scholar’s Year in Review: Navigating the Convergence of AI, Economics, and Physics in 2023”. might be a bit grandiose and bordering on word salad. why the fuck does he think he needs to release preprints. if he had anything worthwhile to say, it would pass peer review
he also has researchgate
Looking to network with other researchers in a diverse array of fields for collaboration and discussion.
bet you would want to, you time-waster
aand his crowning achievement seems to be dead startup where he tries to put covid on blockchain, it has coin and everything. it’s even associated with worldcoin and so with sam altman. curious that