The catarrhine who invented a perpetual motion machine, by dreaming at night and devouring its own dreams through the day.

  • 0 Posts
  • 118 Comments
Joined 6 months ago
cake
Cake day: January 12th, 2024

help-circle


  • It does seem to be the case for me - I’ve seen far less overexcited comments, and far more questioning its present and future abilities to perform.

    I think that at the bottom of the trough people will stop caring about it altogether except for functionality that has been proven to be useful for - such as a translation aid, coding aid, or to quickly pull off multiple images if you don’t mind overall quality.

    I just generated a fresh example highlighting it. I’ll put it inside spoilers to avoid clutter:

    German and English, ChatGPT 3.5
    • [Input 1] translate the following German sentence into English: “der Hund ist schlecht”.
    • [Output1] The dog is bad.
    • [Input 2] Which word is being translated as “bad”?
    • [Output 2] The word “schlecht” is being translated as “bad” in this context.
    • [Input 3] What are other meanings or connotations of the word “schlecht”?
    • [Output 3] In addition to “bad,” the word “schlecht” in German can also mean “poor,” “inferior,” “evil,” or “unwell,” depending on the context in which it is used.
    • [Input 4] Now, translate the sentence “the bad dog is sleeping” into German.
    • [Output 4] “Der schlechte Hund schläft.”
    • [Input 5] Why is it “schlechte” in this sentence, instead of “schlecht” as in the earlier sentence?
    • [Output 5] In German, adjectives change their form based on the gender, number, and case of the noun they are describing. In this case, “Hund” is a masculine noun in the nominative case, so the adjective “bad” (schlecht) needs to take the masculine nominative form, which is “schlechte.”

    It’s working rather well as a translation aid as long as you know the language, as it could help you to phrase a sentence. However, once you ask for specific info - as I did in input #5 - it drops the ball; in this case outputting technically correct but misleading and incomplete info:

    • The form also depends on the article. For example, if I were to use “ein” (a) instead of “der” (the), the correct form would be “schlechter
    • The way that the output is phrased, it implies that the “schlecht” in the first sentence is not describing a masculine noun in the nominative. It is - and the actual reason why it takes the form “schlecht” is not mentioned in the output (predicatives take the base form).

    [und nebenbei: alle Hunde sind gut.]

    In the “overexcitement peak”, I think that a lot of people were focusing on the correct output, and assuming that the rest would be solved “with enough elbow grease”, playing whack-a-mole with hallucinations. Now they’re noticing that it isn’t.





  • That’s some damn great text. It avoids all that discussion about free will, as it focuses on autonomy instead; and it shuts off the “BuT I HaVe NoTHiNg tO HiDe” discourse right off the bat, by mentioning that being watched does change your behaviour

    (BTW, dunno if you guys noticed, but this “nothing to hide” discourse has often the implicit accusation: “since you seek anonymity, you’re assumed to be a shitty person”.)

    A. A Zero-Knowledge Proof system is being trialled at the BBC. Imagine that a minor wants to watch a program for people over 18 years of age. Through this system, which provides a verified identity, the chain will know if the person is of legal age or not.

    Frankly, I feel like the main benefit of such a system won’t be child protection, but shutting up abusive entities that babble shit like “think on the children!”.

    A. Any decision that can significantly affect a person’s life. AI is not a moral agent, it cannot be responsible for harming someone or denying them an important opportunity. Nor should we delegate to AI jobs in which we value the empathy of a fellow citizen who can understand what we feel.

    Emphasis mine. *slow clap*


  • I thought about this a while ago. My conclusion was that the simplest way to handle this would be to copy multireddits, and expand upon them.

    Here’s how I see it working.

    Users can create multireddits multicommunities multis as they want. What goes within a multi is up to the user; for example if you want to create a “myfavs” multi with !potatoism, !illegallysmolcats and !anime_art, you do you.

    The multi owner can:

    1. edit it - change name, add/remove comms to/from the multi
    2. make the multi public or private
    3. use the multi as their feed, instead of Subscribed/Local/All
    4. use the multi to bulk subscribe, unsub, or block comms

    By default a multi would be private, and available only for the user creating it. However, you can make it public if you want; this would create a link for that multi, available for everyone checking your profile. (Or you could share it directly.)

    You can use someone else’s public multi as your feed or to bulk subscribe/unsub/block comms. You can also “fork” = copy it; that would create an identical multi associated with your profile, that then you can edit.



  • By far, my biggest issue with flags in r/place and Canvas does not apply to a (like you said) 20x30. It’s stuff like this:

    \

    People covering and fiercely defending huge chunks of the canvas, for something that is completely unoriginal, repetitive, and boring. And yet it still gets a pass - unlike, say, The Void; everyone fights The Void.

    Another additional issue that I have has to do with identity: the reason why we [people in general] “default” to a national flag, for identity, is because our media and governments bomb us with a nationalistic discourse, seeking to forge an identity that “happens” to coincide with that they want.

    But, once we go past that, there are far more meaningful things out there to identify ourselves with - such as our cultures and communities, and most of the time they don’t coincide with the countries and their flags.

    As such I don’t think that this is a discourse that we should promote, through the usage of the symbols associated with that discourse.

    Maybe where you’re from it’s easy to separate your government flag as its own symbol that doesn’t represent real people

    I think that this is more of a matter of worldview than where we’re from, given that some people in Brazil spam flags in a way that strongly resembles how they do it in USA.




  • Yeah, it’s actually good. People use it even for trivial stuff nowadays; and you don’t need a pix key to send stuff, only to receive it. (And as long as your bank allows you to check the account through an actual computer, you don’t need a cell phone either.)

    Perhaps the only flaw is shared with the Asian QR codes - scams are a bit of a problem, you could for example tell someone that the transaction will be a value and generate a code demanding a bigger one. But I feel like that’s less of an issue with the system and more with the customer, given that the system shows you who you’re sending money to, and how much, before confirmation.

    I’m not informed on Tikkie and Klarna, besides one being Dutch and another Swedish. How do they work?


  • Brazil ended with a third system: Pix. It boils down to the following:

    • The money receiver sends the payer either a “key” or a QR code.
    • The payer opens their bank’s app and use it to either paste the key or scan the QR code.
    • The payer defines the value, if the code is not dynamic (more on that later).
    • Confirm the transaction. An electronic voucher is emitted.

    The “key” in question can be your cell phone number, physical/juridical person registre number, e-mail, or even a random number. You can have up to five of them.

    Regarding dynamic codes, it’s also possible to generate a key or QR code that applies to a single transaction. Then the value to be paid is already included.

    Frankly the system surprised me. It’s actually good and practical; and that’s coming from someone who’s highly suspicious of anything coming from the federal government, and who hates cell phones. [insert old man screaming at clouds meme]


  • Do you mind if I address this comment alongside your other reply? Both are directly connected.

    I was about to disagree, but that’s actually really interesting. Could you expand on that?

    If you want to lie without getting caught, your public submission should have neither the hallucinations nor stylistic issues associated with “made by AI”. To do so, you need to consistently review the output of the generator (LLM, diffusion model, etc.) and manually fix it.

    In other words, to lie without getting caught you’re getting rid of what makes the output problematic on first place. The problem was never people using AI to do the “heavy lifting” to increase their productivity by 50%; it was instead people increasing the output by 900%, and submitting ten really shitty pics or paragraphs, that look a lot like someone else’s, instead of a decent and original one. Those are the ones who’d get caught, because they’re doing what you called “dumb” (and I agree) - not proof-reading their output.

    Regarding code, from your other comment: note that some Linux and *BSD distributions banned AI submissions, like Gentoo and NetBSD. I believe it to be the same deal as news or art.





  • Think on the available e-books as a common pool, from the point of view of the people buying them: that pool is in perfect condition if all books there are DRM-free, or ruined if all books are infested with DRM.

    When someone buys a book with DRM, they’re degrading that pool, as they’re telling sellers “we buy books with DRM just fine”. And yet people keep doing it, because:

    • They had an easier time finding the copy with DRM than a DRM-free one.
    • The copy with DRM might be cheaper.
    • The copy with DRM is bought through services that they’re already used to, and registering to another service is a bother.
    • If copy with DRM stops working, that might be fine, if the buyer only needed the book in the short term.
    • Sharing is not a concern if the person isn’t willing to share on first place.
    • They might not even know what’s the deal, so they don’t perceive the malus of DRM-infested books.

    So in a lot of situations, buyers beeline towards the copy with DRM, as it’s individually more convenient, even if ruining the pool for everyone in the process. That’s why I said that it’s a tragedy of the commons.

    As you correctly highlighted that model relies on the idea that the buyer is selfish; as in, they won’t care about the overall impact of their actions on the others, only on themself. That is a simplification and needs to be taken with a grain of salt, however note that people are more prone to act selfishly if being selfless takes too much effort out of them. And those businesses selling you DRM-infested copies know it - that’s why they enclose you, because leaving that enclosure to support DRM-free publishers takes effort.

    I guess in the end we are talking about the same

    I also think so. I’m mostly trying to dig further into the subject.

    So the problem is not really consumer choice, but rather that DRM is allowed in its current form. But I admit that this is a different discussion

    Even being a different discussion, I think that one leads to another.

    Legislating against DRM might be an option, but easier said than done - governments are specially unruly, and they’d rather support corporations than populations.

    Another option, as weird as it might sound, might be to promote that “if buying is not owning, pirating is not stealing” discourse. It tips the scale from the business’ PoV: if people would rather pirate than buy books with DRM, might as well offer them DRM-free to increase sales.


  • Does this mean that I need to wait until September to reply? /jk

    I believe that the problem with the neolibs in this case is not the descriptive model (tragedy of the commons) that they’re using to predict a potential issue; it’s instead the “magical” solution that they prescribe for that potential issue, that “happens” to align with their economical ideology, while avoiding to address that:

    • in plenty cases privatisation worsens the erosion of the common resource, due to the introduction of competition;
    • the model applies specially well to businesses, that behave more like the mythical “rational agent” than individuals do;
    • what you need to solve the issue is simply “agreement”. Going from “agreement” to “privatise it!!!1one” is an insane jump of logic from their part.

    And while all models break if you look too hard at them, I don’t think that it does in this case - it explains well why individuals are buying DRM-stained e-books, even if this ultimately hurts them as a collective, by reducing the availability of DRM-free books.

    (And it isn’t like you can privatise it, as the neolibs would eagerly propose; it is a private market already.)

    I’m reading the book that you recommended (thanks for the rec, by the way!). Under a quick glance, it seems to propose self-organisation as a way to solve issues concerning common pool resources; it might work in plenty cases but certainly not here, as there’s no way to self-organise people who buy e-books.

    And frankly, I don’t know a solution either. Perhaps piracy might play an important and positive role? It increases the desirability of DRM-free books (you can’t share the DRM-stained ones), and puts a check on the amount of obnoxiousness and rug-pulling that corporations can submit you to.