• 0 Posts
  • 18 Comments
Joined 3 months ago
cake
Cake day: March 9th, 2025

help-circle



  • Well first you need to find a willing partner. Doing this can be scary, but there are a lot of folks who are into it and we should never kink shame.

    Next. Be gentle! Getting one’s anus able to be stretched so large is a huge under taking (get it? UNDER taking?). Always start with a finger and SLOWLY work your way up based on your partner’s direction.

    Hygiene. Gloves are your friend. In most cases you can buy gloves that go up to the elbow at your local farming supply store. Also your partner should be encouraged to do a full bowel irrigation. Unless that’s what you’re into. Again no kink shaming here!

    Finally LOTS of lube. There’s no such thing as too much lube in this case. Be generous and use often.

    With these tips you should be able to master at fis-…. Shit. Well this is embarrassing. Yet I’ve come too far.




  • I asked OpenAI the same. Only without the snark, and noted that US politicians and OpenAI pressers should not be considered evidence without facts:

    Great question—and a healthy dose of skepticism.

    If we assume U.S. lawmakers may be misrepresenting the situation or overstating the threat (intentionally or otherwise), then it’s worth asking: What counter-evidence or independent information exists that disputes the claims against DeepSeek?

    Here’s what we can currently analyze:

    1.

    OpenAI’s Role and Statements

    • The accusation is that DeepSeek used OpenAI data without authorization.
    • OpenAI has not released detailed technical evidence (as of now) proving DeepSeek “stole” data.
    • It is also unclear what “unauthorized use” means here—was it scraping publicly available content generated by ChatGPT? That’s not the same as hacking or violating terms.

    Counterpoint: Unless OpenAI provides forensic evidence (e.g., logs showing data scraping from banned accounts or circumvention of APIs), their claim is not independently verifiable.

    2.

    Open-source AI Training Practices

    • DeepSeek R1 and other models are trained on publicly available data, much like LLaMA, Falcon, Mistral, etc.
    • Many open-source LLMs train on similar corpora, including data from books, code repositories, and even internet crawls, which may contain ChatGPT outputs.
    • No proof has been provided that DeepSeek used proprietary datasets beyond what’s publicly available or scraped from the internet.

    Counterpoint: If DeepSeek simply trained on web data that happened to contain ChatGPT responses (which are abundant online), that wouldn’t constitute theft by typical AI research standards.

    3.

    DeepSeek’s Own Transparency

    • DeepSeek has published detailed model cards and training parameters for R1, a transparency move rare among Chinese AI firms.
    • This suggests a desire to appear cooperative or aligned with global AI openness norms—not necessarily what a covert “spy tool” would do.

    Counterpoint: Spyware tools or state-controlled AI systems don’t usually go open source and document their architectures.

    4.

    No Independent Audit or Third-Party Verification

    • As of now, there’s no independent audit of DeepSeek’s model, training corpus, or infrastructure.
    • The accusations rest heavily on political framing, not technical forensics released to the public.

    5.

    Broader Pattern of U.S. Tech Nationalism

    • U.S. lawmakers have a history of labeling Chinese tech firms as threats without providing concrete, public-facing evidence (Huawei, TikTok, etc.).
    • This doesn’t mean the threats are false, but it does mean we should demand proof beyond committee soundbites.

    TL;DR – Is there counter-evidence?

    Not conclusive counter-evidence, but there’s a lack of compelling public proof supporting the claim. The case against DeepSeek is built on:

    • OpenAI’s statements (without shared evidence),
    • Political concerns about China,
    • and suspicions rooted in strategic competition.

    That’s not enough to say DeepSeek is innocent—but it’s not enough to prove guilt either










  • You can think that, but it’s wholly inaccurate. Especially these days.

    The more people that engage with an artist’s work in any way online, the more analytics teams see that. They then note a steady demand for content around said IP. In order to create more content, the creator/author must be compensated even if not directly involved. If that compensation goes to a living person who willfully and knowingly uses it to justify horrendous actions, then every single person in that line of consumption is culpable. Starting with the consumer. Us.

    This is exactly why they keep creating more shit for this franchise. It’s because people keep engaging and supporting it and demanding more. So then the author (who is btw on record as saying that her continued success is proof that people support her opinions), keeps getting richer and richer and goes on to have bigger platforms and unchecked actions.

    As a trans person, if I knew any action taken by myself or a family member contributed even a small fraction of a percent of a single cent to that thunder cunt, I’d be nauseated.

    Bottom line, real people > fake wizards.

    But that’s me. You do you.



  • lemmy_acct_id_8647@lemmy.worldtoADHD@lemmy.world*Permanently Deleted*
    link
    fedilink
    English
    arrow-up
    2
    arrow-down
    1
    ·
    edit-2
    3 months ago

    I’ve had good luck with Talkspace. Unfortunately (for a plethora of reasons) I’m in the US so I can’t speak to its availability in the EU, but my personal experience has been great as I’m able to seek therapists/psychologists for talk therapy, and also psychiatric care for meds as needed.

    EDIT to add: The main reason I prefer Talkspace to other platforms is because they take insurance. Again, primarily a US problem, but noting for others who may see this.