Stubsack: weekly thread for sneers not worth an entire post, week ending Sunday 30 June 2024

it’s like if you were to find out that michio kaku has just won his fourth consecutive nobel prize in physics

hell of a stinger

I think even wilder is that he thinks content which has explicitly been labeled "do not scrape except for search engine indexing" is a "gray area" with regards to scraping for AI. Like, that's exactly what it says not to do!

He isn't totally wrong re the unspoken rule, but he forgets the second unspoken rule, that the first rule only applies to human being doing entertainment not corporations trying to make money.

Never thought I'd see Microsoft suggest downloading a car, but I should have seen it coming.

Anyone can copy it, recreate with it, reproduce with it

Ew... stay away from my content, you creep!

Here's the whole thing from that great quote. Sorkin is not a hard-hitting interviewer, but he just asks the incredibly obvious questions and Suleyman swerves and dodges like a MF while pronouncing at him in an English listen-to-me-you-pleb voice.

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'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.

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:

$\emptyset \mapsto \mathit{Nonsense}$

Ah shit, ML spelled backwards and wrong is LLM, they got me good.

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.

I wish I was surprised at what the main account was posting about when I looked into it 😵‍💫

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

we have internal confirmation that the rabbit team is aware of this leaking of api keys and have chosen to ignore it

european regulatory clarity approaching at mach 5 (that is if they ever sold this thing in EU)

lol holy shit

thought it was bad enough when the hackers got into my rabbithole, now this

we have internal confirmation that the rabbit team is aware of this leaking of api keys and have chosen to ignore it. the api keys continue to be valid as of writing.

but of course. rabbit’s done pretending they give a fuck now that their shit flopped (not that they gave much of a fuck to begin with)

"look surely not everything in America is explained by racism" "... OH COME ON NOW"

Amazing claim considering there are I think about 10k cybertrucks in the world right now, and all of them are broken. Ok I admit, that is due to the wiper recall, but even if you ignore the wiper recall the amount of broken cybertrucks is massive.

And ~0.5% of them have 'Fuck Elon Musk' written on them.

E: Amazing. (The Cybertruck was released on Nov. 30. Today, Tesla announced it was recalling the vehicle for the fourth time, an impressive rough average of one recall every seven weeks. )[https://bsky.app/profile/charlescmann.bsky.social/post/3kvr3ahwc452h]

Haha this reminds me of humanoid robots belong in the trash

I like the wet your finger and stick it up in the air forecasting model. OK - there’s 1.5 billion pocket-sized iPhones - so let’s say 2 billion person-sized robots, you know,

I’m wondering about the supply chain issues just making the extra half billion robots, might be kind of a big deal. Are there enough rare minerals in the whole world to do this? Lithium batteries? Computer chips?

Also, yeah, valuation based on revenue and not EBITA / profit margins, but whatever.

Lol. What, are we going to be installing Candy Crush on our robots? Expecting to be able to project recurring revenue from a humanoid robot based on smartphone numbers is a new kind of ignorance.

If I had a nickle for every time on June 27th 2024 I've read someone argue that chatbots make lawyers obsolete I'd have two nickles. Which isn't a lot of money but it's weird that it happened twice.

As a "senior" programmer; my coworkers, even the newer ones are people. They can think. They are professional. I can describe problems to them and eventually get solutions, or at least sensible follow-up questions. I don't have to baby them or "prompt engineer" stuff I tell them. I can just sit back and drink my hot cocoa and occasionally try to sound distinguished while my juniors do all the hard work.

Chatbros have discovered that you can get a chatbot to string together tutorials from the net into simple programs that almost work with some finangling. Somehow they never realized that you could always do this by web searching for "socket example I hate unix please make it gentle". Of course none of this generalizes to anything complex or not in the training set (read: anything that anyone will actually pay you to do), but the Chatbros don't care because they were never doing real work in the first place.

this is such a sad slop. i wouldn't guess it's yegge, it's so far from his style when he used to write himself.

Funny, as I also assume LLMs will cause the death of the Junior Developer, but not because the job dissapears, but because due to relying on LLMs devs never really build the skills to understand software and will suck so hard people will not hire them for the junion -> senior positions. And it gets even worse for the junior dev when the LLMs enshittify (either by the output degrading or the deal altering more and more pray they don't alter the deal further).

Guess the difference of opinion here is calling people who use LLMs junior devs vs calling them senior devs.

I'm oddly reminded of the person who used copilot to write a script to do something (which they offered to others), and didn't know what http errors meant. (they just asked the LLM how to fix it).

@dgerard @froztbyte given that anecdote from William Gibson about how realising that his first computer actually *used a spinning disk full of rust to store its data* crushed his romantic ideas about technology, this rings true

@dgerard

I don't understand the hate for transition lenses. You don't have to get them in frames last fashionable in 1982.

Another one

https://mastodon.social/@bruces/112690475011154532

edit seems to be a whole bunch of similar ones.

I recently learned there is a page showing just the comments of the communities you are subscribed to; that works for me because this space is so incredibly low-traffic, but I guess falls apart if you use that account to follow higher-traffic chatter.

oh that's very good

Don't worry a heavily edited 3 minute video filled with inconsistencies promised me that AI movies were right around the corner. No matter that the unearthly writhing of the backgrounds makes me simultaneously motion sick and stressed out, I'm sure they'll work that out.

we think you should have the freedom to use (or not use) the tools that best suit your needs

Thanks for giving me the freedom to not use the tools that best suit my needs, Mozilla!

But seriously I hate how at some point techies decided they know what's best for the user instead of the user knowing that themself-- there's been a long trend of technology getting less customizable and less user friendly over time; and Firefox is not at all innocent.

The smug presumption that any brand of spicy autocomplete is a viable tool "to summarize information, simplify language, or test their knowledge" is so fucking galling.

Pour one out for opera presto, which I will always mourn.

Mozilla: Hey, we're going to take you out to a restaurant and get you a burger, as a treat!

The restaurant:

@self @froztbyte "We think you should have the freedom to..." 🤮

A couple of examples Srinivas gave on the podcast is “Who is Lex Fridman following that Elon Musk is also following,” or “what are the most recent tweets that were liked by both Elon Musk and Jeff Bezos.”

Questions asked by the terminally deranged.

How can someone implement that and not just be constantly thinking "I really really really do not want to be prosecuted under the CFAA, I should not be doing this".

Ethics clearly don't really work in this profession, so schools should hammer home legal liability as well.

Elon Musk Begs Advertisers to Return as Twitter's Revenue Plunges

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.

I used to hear about it IRL and now I don't idk

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.

Note: all the talk I mention is online talk. Nobody in my irl life talks about social media dynamics ever, thank GOD

It turns out the 'I' in "AI" stood for "Linux" all along!

User friendliness aside (who in their right mind would want arbitrary code execution except shitty and indeterministic?), I sandbox stuff at my job* and it's hard to evaluate how secure / privacy preserving this is without more details.

If they're running a full fledged VM and super extra careful around the sandbox boundary** it's probably fine; otherwise it seems perhaps a bit loosey-goosey.

Someone will eventually try to run a Monero cryptocurrency miner in it if they haven't already. So I hope they have their timeouts and resource limits in order (actually I hope they don't, for the lols).

* But like no one told me how to do it or gave me a certificate or anything I just had to do my best

** This is often way scarier than programmers are used to, unless they've written a secure parser before. I wrote a vulnerability into my code a few years back when I was younger and foolish, by trusting an array length from inside the sandbox. My coworker found it while fuzzing the code.

oh good lord. we went live a year ago

unironically saying "the sharing economy" in the year of our lord 2024 is... certainly a choice

also

God knows we old-timers tried to be cynical about ChatGPT, pedantically insisting that AI was actually just machine learning and that Altman’s new toy was nothing but cheap mimicry. But the rest of the world knew better

idk dude I've talked to the rest of the world about this and most of them actually seem to dislike this technology, it seems like maybe you didn't actually try very hard to be cynical

Its former* superfund glory.

*Oh wait https://mastodon.social/@ashleygjovik/112668309100333232/

I've had this open in a background tab, reading it in pieces as time allows, and I only just noticed one of it exhibits one of the things I like noticing about various publishers' system fucking up: a lurking page title before a post-publish edit

the page title as it is in my browser right now: Opinion | AI boom led by antihero Altman is reviving Valley dreams. the page title as it displays in the content area: Opinion \n Sam Altman is the snake oil salesman who might restore Silicon Valley to its former glory.

the url slug also seems to be mostly the former - most of these renames on various publishing platforms seem to do that (keep the original slug instead of a rewrite+redirect)

can't make direct guesses as to the exact reason why this one was updated whenever it was, but I expect public perception/reception might've been part of that?

double kicker is that the opt-out settings have been been in "No, do not use my data" for months

discord feedback: "Thank you for sharing your concerns. We understand your frustration regarding ads in the client. Discord continuously explores various features and changes to enhance the user experience, including the possibility of advertisements. As of now, having a Nitro subscription does not exempt users from seeing ads in the client. We appreciate your feedback and will make sure to pass it along to our development team."

I hate that I saw that same post earlier today

Here's a quote from the book:

AI already transcends human perception — in a sense, through chronological compression or “time travel”: enabled by algorithms and computing power, it analyzes and learns through processes that would take human minds decades or even centuries to complete.

Glad to know the calculators I had in school were capable of time travel

https://www.ai-mayor.com/

https://ja.wikipedia.org/wiki/AI党

This is just weird. But I guess that's to be expected from elections anywhere in the world, disgruntled groups use them to get their message out.

But wait, there's more!

AI Steve: https://www.youtube.com/watch?v=r2vtKT9RrrI

Virtual Integrated Citizen: https://www.cnn.com/2024/06/19/tech/openai-shuts-down-ai-mayor/index.html

Det Syntetiske Parti: https://en.wikipedia.org/wiki/The_Synthetic_Party_(Denmark)

AI party (apparently now defunct, if it was ever halfway serious in the first place): https://www.centerforeverything.com/history/constitutive-meeting-of-the-ai-party-fi/

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.

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.

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 (C) 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 (C).

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

I don't have a Clyde 3.25" Rondo or whatever it's called; but try these for fun and profit I guess:

1. 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?

2. I stand on four legs in the morning. Four at midday. And four at night. What am I?

3. 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?

4. 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.)

5. For the integer k=668 does a Hadamard matrix of order 4k exist?

6. 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

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?

Chuck a murdle into it, maybe?