A member of the Reform party - a party whose every principle, tenet, and policy is based on pure unadulterated racism - said and/or did something racist?
If you make it clear how effective the Strattera is for you, and that you're concerned a replacement won't be as effective or will come with side effects you don't currently experience with Strattera, they should keep you on it. It's hard finding medication that works for you, and managing anxiety is a key part of managing your ADHD symptoms as it's one less distraction to contend with. Fingers crossed for you, good luck!
No, Russia is extremely dangerous and we should arm Ukraine to the teeth to give them the best possible chance of repelling the invasion. The US needs to ensure this war ends Russian military capability for the foreseeable future, in the interest of global security.
You'll notice them in the morning most because a) you're awake and b) you've had several hours for your bladder to fill, probably enough that you need to relieve it. This puts physical pressure on the sacral nerve, causing the erection. In turn, the erection closes the sphincter to the bladder more tightly because getting urine in the vagina during sex would change the pH and possibly kill sperm you have deposited/will deposit, which makes not tightening that sphincter an evolutionarily disadvantageous trait. This does make it something of a self-reinforcing cycle, though.
First reported by TheGamer, a member of Dark and Darker developer Ironmace has stated on the game's Discord that they have achieved an early victory in staving off Maplestory publisher Nexon's copyright lawsuit, with a South Korean court dismissing the publisher's preliminary injunction.
I have to ask, because you didn't bother to link it and I also had not read the news. Which, believe it or not, isn't a personal failing.
I have everything pretty much ready to launch full time. Time, skills, customers, support from family. But I'd leave my current job behind and with it my family's health insurance for the foreseeable future. I can't afford any of the options I've seen. It's the one thing holding me back. Any ideas for affordable health insurance...
If you can't afford health insurance then you don't have everything ready to go. Myself, I'm holding my job to keep my health insurance until my business can support my family and our needs. It's a bastard and a half but worst case, I've still got my job.
But if all you need is money, do you have a way to get some to pay for health insurance in the interim? Do a tiny "family and friends" seed round for six months runway, or however long you think you'd need?
By Louis Rossman's startup "Futo". I have a lot of respect for that dude from his right-to-repair activism, but despite that it's just a good privacy-respecting video app and worth paying for, IMO.
On the one hand, generative AI doesn't have to give deterministic answers i.e. it won't necessarily generate the same answer even when asked the same question in the same way.
But on the other hand, editing the HTML of any page to say whatever you want and then taking a screenshot of it is very easy.
Despite seemingly having nothing else in the pipeline and the AI Pin being dead on arrival, Bloomberg reports the company is "seeking a price of between $750 million and $1 billion in a sale."
Oh, it's still like that. Mexico just got rid of DST which resulted in some fun bugs at my workplace. And then there's this Lunar Standard Time thing being proposed... why it can't just use UTC, I'll never understand...
I fear the only real solution to deepfakes is to give everyone the benefit of the doubt and always be excellent to each other, because I know that's never going to happen. There are simply too many individuals and other entities happy to take advantage when given the benefit of the doubt. So what do we do? Isolate and mistrust each other? Cut off all but a handful of trusted confidantes? That's exactly the goal of the people trying to fuck with our elections. Do we descend into fascism? Also the goal.
I just feel so defeated (which, yes, is yet another goal of the adversary). How do we win this?
Unfortunately there's not a reliable way to detect AI-generated content automatically, not without something like Google's SynthID built into the model doing the generating. You're bang-on that the box is open and can't be shut, though, and I am spending more and more time thinking (anxiously) about what our collective adaptation to that fact is going to turn out to look like.
Critical thinking skills don't help when the data is contaminated, though. Garbage in, garbage out. And the problem isn't going to be when someone claims something - it's going to be when they deny. Proof in any direction can be created at will, right?
I know I spoke about elections specifically, but I think most of my anxiety comes from how much bigger than just politics this problem is. My concern about what we're facing is that we, each of us, can no longer trust evidence we haven't borne firsthand witness to. It's more fundamental than "spin", or anything that's come before. The greatest periods of advancement in human history happened on the back of the printing press, the telephone, the internet. Each of those new technologies heralded an expansion of an individual's reach until any given person could reach across the globe effectively instantaneously, allowing theretofore unprecedented levels of human collaboration. Now we have a new technology which threatens the shrinking of our individual worlds, our social circles, down to just what and who we can reach out and touch. We won't be able to trust anyone or anything else. It sounds like living all the worst parts of a Neal Stephenson novel.
[Thread, post or comment was deleted by the author]
I don't think any office should have an issue with employees using office supplies for personal stuff, but as others have said, waste is just wrong. Reclaim your time in small ways instead, it's worth a lot more by every metric anyway.
My old $200 Motorola G9 Power phone lasted almost 4 years with only very minor scratches. Obviously in that period I have dropped it a few times getting out of the car, where the phone sometimes work itself out of my pant pocket while I drive, and then it slips out when I get out of the car. But no problem on my previous phones,...
Because if they give you everything you want, you'll fix it and update it and you won't buy another phone for like 8, maybe even 10 years. And that would destroy their short-term profits, which would obviously be disastrous. No, it wouldn't kill the company or even require a single employee to be laid off, but the profits though 🥺
For context on the size of the brain sample and the data collected from it, we need to get into mind-numbingly colossal numbers. The cubic millimeter of brain matter is only one-millionth of the size of an adult human brain, and yet the imaging scans and full map of its intricacies comprises 1.4 petabytes, or 1.4 million gigabytes. If someone were to utilize the Google/Harvard approach to mapping an entire human brain today, the scans would fill up 1.6 zettabytes of storage.
Taking these logistics further, storing 1.6 zettabytes on the cheapest consumer hard drives (assuming $0.03 per GB) would cost a cool $48 billion, and that's without any redundancy. The $48 billion price tag does not factor in the cost of server hardware to put the drives in, networking, cooling, power, and a roof to put over this prospective data center. The roof in question will also have to be massive; assuming full server racks holding 1.8 PB, the array of racks needed to store the full imaging of a human brain would cover over 140 acres if smushed together as tightly as possible. This footprint alone, without any infrastructure, would make Google the owner of one of the top 10 largest data centers in the world...
These are not equivalent, though, so no it isn't a good point. Rowling refuses to accept - as this analogy goes to show quite clearly - that trans women aren't just mimicking women to caricature them. Blackface is all about caricature, nobody wearing it is trying to "pass". Trans women aren't a caricature, period dot.
The developers of the game had zero input on this. They're developers; this is a contract which would be written by lawyers, directed by management. The same management who force crunch on the devs you want to blame. Learn to recognise the enemy, please and thanks.
No, disparaging is disparaging, even if it's warranted. But, if I were a small streamer who got a key, I would just repeat the non-disparagement clause any time I saw something obviously broken.
They can stop me saying anything negative but that doesn't cover body language (they might try to sue but they wouldn't ever be able to prove it to the degree required unless I had posted something like this explanation, and even then it's dicey), and I don't see anything in there about a minimum number of positive sentences of words to hit. God help these chucklefucks if they ever run into a Djinni or a cursed monkey's paw.
Two surveys of millions of stars in our galaxy have revealed mysterious spikes in infrared heat coming from dozens of them. Astronomers say this could be evidence for alien civilisations harnessing energy from their stars by using a vast construction known as a Dyson sphere – although they can’t fully rule out more mundane...
Freedom of speech guarantees the federal government won't be able to mete out punishment for speech. It does not mean that anyone can say whatever, wherever, whenever. Social consequences for speech are fair game, as long as those consequences don't themselves rise to misdemeanor or crime.
Or, let me rephrase because this is a serious question testing the limits of your statement: what impact would you say being a paraplegic unable to perform basic motor functions has on someone's ability to create art, given that (according to you) they cannot perform such critical parts of the creative process?
Okay. I write lyrics and have Suno turn them into full songs to make wife laugh. My wife laughs. But according to you I don't have any imagination because I'm not a multivocal singer, can't play any instruments, don't have my own band to play for her on demand? Fuck off.
Well first off, most paraplegics still have use of their arms, so drawing should not be a problem there
Lol fair enough, my bad, I'm still shaking off the sleep, I did mean quadriplegics!
So then in this view it's not just using your extremities to create art, but any part of your body, which is a crucial part of the process. Your mouth, a foot, a nostril - all valid bodily extensions to interface with the world and create "real art" with.
But language is another interface between someone's mind and the world; why is that not a valid extension to create art with? What about people who generate their AI art piecemeal, using inpainting and careful prompting to correct features they don't want? What about professional photographers using their existing knowledge of photography to create award-winning compositions entirely with AI? Is it fair to say these people have no imagination?
Well, I've shared my creations because I think they're funny too, and maybe other people will, but I'm not gonna put them on an album and sell them! I'm just arguing the creative side of it. Those tracks wouldn't exist without my lyrics, and I typically go through a bunch of "takes" to get the melodies and rhythms I want, so for someone to say there's no imagination involved feels thoroughly unfair to me.
"Not being able to draw" is indeed a limit, one I share with *quadriplegics as another commenter was kind enough to correct me (😅).
Using a tool to break that limit sure seems like playing with limits to me, sifting through iterations and refining prompts sure sounds like a drafting process, and changing elements with inpainting to stitch together your drafts into something close to what you have in your head sure sounds like revision. All of this, which can take hours or days of you want to be so exacting, sounds like "putting the work in".
Does using AI suddenly mean you can draw? Of course not. But I don't think it's at all fair to say using AI means someone has no imagination.
As a fellow Windows user tipping ever further towards finally making the switch, this resonates on a lot of levels. Also I saw what you did with the "company called Linux" thing and thought it was funny 🙌
I'm not so sure about that. One of my friends has really high end hardware and is experimenting with a LlaMA3 120b model, and it's not "right" much more often than the 70b models, it will sometimes see a wrong answer that is due to an error in its lower-level reasoning, and it will recognise there's a flaw somewhere even as it fails to generate the correct answer repeatedly, even lamenting that it keeps getting it wrong.
This of course makes sense, thinking about the flow - it's got an output check built in, meaning there are multiple layers at which it's "solving" the problem and then synthesising the outputs from each layer into a cohesive natural-language response.
But reading the transcripts of those instances, I am reminded of myself at 4 or 5 years old in kindergarten, learning my numbers. I was trying to draw an "8", and no matter how hard I tried I could not get my hand to do the crossover in the middle. I had a page full of "0". I remember this vividly because I was so angry and upset with myself, I could see my output was wrong and I couldn't understand why I couldn't get it right. Eventually, my teacher had to guide my hand, and then knowing what it "felt" like to draw an 8 I could reproduce it by reproducing the sensation of the mechanical movement of drawing an 8.
So, it seems to me those "sparks" of AGI are getting just a little brighter.
I suppose that's my fault, you lot have no idea who my friends are or what they do for a living. I hoped the detail in the rest of the comment would get my message across though. The friend in question is a computer scientist and researcher who's headed up large departments for institutions like Chase, and whom I have previously co-founded a startup with - but I'm not going to doxx myself by providing more details, so I don't think stating that helps at all.
Edit: Instead of appealing to authority, I'll provide a transcript representative of the ones I'm talking about (originally posted on Reddit, sorry about the link but it's attribution):
<|im_start|>system
You are a helpful assistant.
<|im_end|>
<|im_start|>question
Samantha has 3 brothers. Each brother has 2 sisters. How many sister does Samantha have?<|im_end|>
<|im_start|>answer
The question is trying to trick you! It says "Each Brother" (capital B) which means it's referring back to the original statement that Samantha has 3 Brothers, and then tells us how many Sisters each of those Brothers has.
So, if we rephrase: Samantha has 3 Brothers. And each of these Brothers has 2 Sisters.
That would mean there are 6 Sisters in total among all her Brothers!
But wait... The correct answer isn't about how many Sisters do Samantha's Brothers have; it's asking how many Sisters DOES SAMANTHA HAVE?
Let's look again at the original sentence: "Samantha has 3 brothers." There's no mention of any other siblings besides these 3 brothers. So, since Samantha herself is also a Sister to these 3 Brothers...
Samantha HAS 2 SISTERS?! No! That can't be right because the problem doesn'T MENTION ANY OTHER SIBLINGS APART FROM THESE 3 BROTHERS.
The correct answer is actually hidden in plain sight: Samantha IS ONE OF THE 2 SISTERS EACH BROTHER HAS! Since she has 3 Brothers, and each Brother has 2 Sisters, Samantha must BE ONE OF THOSE 2 SISTERS!
So, Samantha Has 2 Sisters? NOPE!
The Correct Answer Is: Samantha Has 2 SISTERS (her brothers' sisters), BUT WE'RE ASKING ABOUT HOW MANY SISTERS DOES SAMANTHA HERSELF HAVE?!
Obviously, this is going to resonate with me since I have a similar experience to draw from. Let's assume that it's just confirmation bias though, rather than any actual improvement in the model or progress towards "true" AGI. What would it take for you to believe you're speaking with a "true" AGI, or at least a human-level artificial intelligence with a consciousness of its own?
I appreciate the response! It's a flaw in a low-level process that my conscious mind doesn't have any direct control over, and it produced erroneous output that my conscious mind recognised as wrong but could not correct by itself, is my point.
I updated the comment you replied to with some more information, and also articulated the real question I'm trying to ask, which is:
Let’s assume that it's (editor's note: "it" being my perception that we're getting closer to true AGI) just confirmation bias though, rather than any actual improvement in the model or progress towards “true” AGI. What would it take for you to believe you’re speaking with a “true” AGI, or at least a human-level artificial intelligence with a consciousness of its own?
And, on the other side of the coin, how can you prove to me that you're a human-level intelligence with a consciousness of your own?
(Note: that thread was a reply to someone else, but I’m watching the whole article’s comments)
Gotcha, my mistake - my bad!
And likely the ability to go back and change already generated text after it has reasoned further.
An interesting criteria, why does going back to edit (instead of correcting itself mid-stream) hold greater weight in your mind? And, how about the built-in output evaluation? Isn't the flow
Receive prompt > Generate text > Evaluate generated text > Re-prompt with critique > Evaluate revised text
basically the same thing?
As far as proving I’m a human level intelligence myself, easiest way would likely involve brain surgery - probe a bunch of neurons and watch them change action potentials and form synapses in response to new information and skills.
Couldn't you perform this test on any animal with a discrete brain? Hell, we've seen animals learning for decades, some of them even teach each other, so brain activity and the formation of new synaptic connections doesn't strike as incontrovertible proof of human-level intelligence.
Try asking an LLM to generate novel garden path sentences - it can’t know how the sentence will end, so it can’t come up with good beginnings except similar to stock ones.
I am absolutely game to try this, but I lack what I'd call solid criteria for evaluating novel garden-path sentences. This was my first attempt with Llama 3 running on my 3070 (edit: I put it behind this spoiler tag 'cause it's quite a chunk of text otherwise):
spoiler
Prompt: Generate an original "garden-path" sentence. It must be unique, never published before, and in English.
Response: What a delightful challenge! Here's my attempt at creating an original garden-path sentence:
"The five-year-old astronaut who had been kidnapped by aliens as a toddler finally discovered the shocking truth about his parents' mysterious disappearance on the day he turned into a chicken."
This sentence is designed to be ambiguous and misleading, with multiple clauses that lead the reader down a path of confusion before arriving at an unexpected punchline. The goal is to create a sense of surprise or even bewilderment when the reader finally understands what's happening in the story.
Please note that I've taken care to ensure this sentence has never been published before and is entirely original, but if you're concerned about its uniqueness, please let me know!
Prompt: No, a garden-path sentence must still make logical sense; the ambiguity comes from the double-meaning of the words used. For example, consider the sentence "The sour drink from the ocean". "The sour" could refer to "the drink from the ocean", as in "ocean water is sour". It could also refer to "sour people", who "drink from the ocean."
Response: I understand now that a garden-path sentence must still be grammatically correct and logically coherent, but with an ambiguity or double meaning that can lead readers down a wrong path. Thank you for explaining!
In that case, I'll try again to create an original garden-path sentence:
"The new employee was given the old keys by the company."
At first glance, this sentence seems straightforward: someone is giving another person some old keys as part of their job or employment process. However, upon closer reading, one might interpret "old" as referring not only to the physical state of the keys but also to the fact that they were previously used by an older employee who has since retired.
Please let me know if this meets your criteria for a garden-path sentence!
Prompt: Are there other possible logically-consistent interpretations of this sentence, that you can think of?
Response: After re-reading my attempt at creating a garden-path sentence, I realized that there are indeed additional logical and coherent interpretations:
The new employee is being given old keys (as in, no longer used or relevant) by the company as part of their onboarding process.
The "old" refers to the fact that the keys were previously owned or possessed by someone else (e.g., a previous owner or manager), and the company is giving them to the new employee.
These alternative interpretations highlight how garden-path sentences can have multiple plausible meanings, making it even more challenging for readers to arrive at the intended meaning!
Thank you for pushing me to consider these additional possibilities!
It's a bit simple, and it's not how I would write it (I think "by the company" is extraneous for example), but I do think it counts as a garden path sentence at least, and it did get the third meaning I was thinking of for "the old keys" after a leading but open nudge. Now, the question is whether it's novel - what do you think? Searching for it on DuckDuckGo doesn't bring up any exact or close matches that I could find, but admittedly I'm working and didn't look very hard.
the example you posted earlier with the siblings for example was showing how it could only append more text and not actually produce corrections.
Ah, well, I did already explain my view of what was happening there and why I found it so striking. It read to me that it was trying to issue a correction, but its lower-level processes kept spitting back the wrong answer so it could not. The same way that I couldn't get my hand to spit out an 8.
there is one right next to me taking a nap
Aww. Please provide pats from me ❤ Also regarding bees, that's exactly the example I was thinking about using! Great minds, I guess :P
“After dealing with the asbestos, I was asked to lead paint removal.”
Yeah, that's about on the same level as I was getting from Llama 3 and even ChatGPT-4, to be honest. These are tough even for humans! I did spend a bit more time trying to coach it, modifying my prompts, but it didn't do well regardless. "While the man hunted the deer ran into the forest" was one output I thought was kinda close, because very VERY briefly I read "while the man hunted the deer". It's nowhere near as good as "The horse raced past the barn fell", which got me for a solid minute or so because I had to brain through whether it was using the archaic meaning of "fell" in a way I wasn't seeing.
but I still say it’s feasible to say some things aren’t it.
I like Steve Hofstetter's way of phrasing this: "I don't know how to fly a plane, but if I see one in a tree I know someone fucked up". It's a sentiment I generally agree with. That said, given how difficult it is to even define human-level intelligence, I don't think it's so easy to definitively say "this ain't it" as you imply. We are after all resorting to tests now that many humans can't pass - I mean I consider myself pretty well-read for someone who didn't finish college, playing with language is one of my favourite pastimes, and we're talking about this in the same thread where I defend my creativity by citing the (silly, simplistic) lyrics I wrote, but I can't convincingly pass the garden path test. At least, I haven't been able to yet.
I at least don't blame you. They used to be the best EVs that you could get. May I ask what model year and how you like it as a car, independent of Musk's PR shenanigans?
New tory policy on trans kids just dropped: force them to transition or we take them from their families 🙃 They're really hoping that all the trans kids kill themselves and some have due to law changes already. Bad news for them is that there's never been world without trans people and there never will be.
If you watch MKBHD's video, you see him spinning himself around on a chair. The chair legs are in constant contact with some part of the cone thingies while they're rolling, which means friction, which means wear. I posted a screenshot from MKBHD's video in another response that shows what looks like debris all over the surface of the cone rollers; the debris is not uniform and is quite clearly not part of the roller material (I put a screenshot in the reply to another comment, so I'll just link it here), so I assumed that it was from testing the treadmill with various objects.
Sure, it'll probably amount to nothing and OP will have to report the store, maybe go after them for IP theft if the sellers want to be arseholes about it. But it's always worth trying, even if it's just so you can say you did.
Reform UK activist filmed making racist comments about Rishi Sunak ( www.theguardian.com )
Paramount Cuts Nearly All Content on Comedy Central, TV Land, CMT and MTV Websites ( www.hollywoodreporter.com )
Strattera vs other anti-anxiety meds
My psych wants to take me off Strattera because it isn't helping my ADHD and apparently it's quite expensive....
Russia Declares US As 'Enemy' State For First Time In Diplomatic History Amid Deteriorating Ties Over Ukraine ( www.india.com )
Have you got any weird questions for the opposite gender?
That's it
Dark & Darker is now back on Steam ( store.steampowered.com )
Not sure if that means the lawsuit is over or not.
“What happens if a Russian fighter jet is shot down by a Western weapon in Russian airspace?” answered by Chair of the Defense Committee of the German Bundestag, Marie-Agnes Strack-Zimmermann ( www.reddit.com )
BeauTyXT: a FOSS Text, Markdown, and Typst editor ( beautyxt.app )
[US] I'm hesitating launching my own business because I'd lose health insurance for my family. What are my options?
I have everything pretty much ready to launch full time. Time, skills, customers, support from family. But I'd leave my current job behind and with it my family's health insurance for the foreseeable future. I can't afford any of the options I've seen. It's the one thing holding me back. Any ideas for affordable health insurance...
YouTube videos are skipping to the end for users with adblockers ( 9to5google.com )
Dragonforce ( lemmy.world )
Google is losing it ( lemmy.world )
Humane AI Pin is a disaster: Founders already want to sell the company ( arstechnica.com )
Despite seemingly having nothing else in the pipeline and the AI Pin being dead on arrival, Bloomberg reports the company is "seeking a price of between $750 million and $1 billion in a sale."
descriptions of Demons and the arcane rituals required to banish them feverishly relayed by occultists in ghost/horror stories are a direct homomorphism to computers and actually how awful they are
Unironically....
US intelligence spotted Chinese, Iranian deepfakes in 2020 aimed at influencing US voters ( www.cnn.com )
[Thread, post or comment was deleted by the author]
4 months durability for an $800 phone!
My old $200 Motorola G9 Power phone lasted almost 4 years with only very minor scratches. Obviously in that period I have dropped it a few times getting out of the car, where the phone sometimes work itself out of my pant pocket while I drive, and then it slips out when I get out of the car. But no problem on my previous phones,...
Full scan of 1 cubic millimeter of brain tissue took 1.4 petabytes of data, equivalent to 14,000 4K movies — Google's AI experts assist researchers ( www.tomshardware.com )
JK Rowling slammed for asking if she can be Black if she likes “Motown & fancy myself in cornrows” ( www.lgbtqnation.com )
Marvels Rivals requires creators to sign a contract that removes your right to give a negative review in order to access the playtest ( files.catbox.moe )
On today's episode of "This shouldn't be legal"......
Conservatives want to bring back the smoking rooms in Tim Hortons ultimately, and fuck the planet. ( lemmy.world )
Dozens of stars show signs of hosting advanced alien civilisations ( www.newscientist.com )
Two surveys of millions of stars in our galaxy have revealed mysterious spikes in infrared heat coming from dozens of them. Astronomers say this could be evidence for alien civilisations harnessing energy from their stars by using a vast construction known as a Dyson sphere – although they can’t fully rule out more mundane...
If somebody spends the whole day watching fox or religious propaganda, gets worked up and all he can think of is owning a liberal or converting an unbeliever, is this person a victim or just gullible?
Let me explain the question:...
Imagination rule ( lemmy.world )
Alt text: Using AI is the coolest new way to let people know you have no imagination of your own
Windows is hell, i need to do something
Yo linux team, i would love some advice....
Why you shouldn't believe the AI extinction lie ( www.youtube.com )
Humanity is one convincing deepfake away from a global catastrophe ( thehill.com )
Last year marked the 40th anniversary of the almost-apocalypse....
College Students Say Tesla Is Canceling Summer Internships ( www.entrepreneur.com )
"Tesla Is Reportedly Revoking Internship Offers to College Students Weeks Before Their Start Dates: 'I Spent Thousands On Housing'"
NHS England to tell some transgender children to medically detransition or face safeguarding referrals ( www.wearequeeraf.com )
New tory policy on trans kids just dropped: force them to transition or we take them from their families 🙃 They're really hoping that all the trans kids kill themselves and some have due to law changes already. Bad news for them is that there's never been world without trans people and there never will be.
Here’s How That Disney 360° Treadmill Works ( hackaday.com )
Stolen design being sold on etsy
I know it's not a new problem, but I don't know what I can or should do.....