Skip Navigation
Posts
1
Comments
163
Joined
11 mo. ago
  • West has fallen. Billions must post.

  • I mean, because it's a risk that's obvious even to me, and it's not my job to think about it all day. I guess they could just be stupid. 🤷

  • That's cool. Obsidian is the strongest block so I bet it's a very effective weapon.

  • Meow, meo meow meow mao meow, meow meow mrrp meow. Meow meow meow meow meow... 😿

  • chat when will the horrors end

  • I’m not sure I understand what you’re saying. By “the commenter”

    I was talking about you, but not /srs, that was an attempt @ satire. I'm dismissing the results by appealing to the fact that there's a process.

    negative reward

    Reward is an AI maths term. It's the value according to which the neurons are updated, similar to "loss" or "error", if you've heard those.

    I don’t believe this makes sense either way because if the model was producing garbage tokens, it would be obvious and caught during training.

    Yes this is also possible, it depends on minute details of the training set, which we don't know.

    Edit: As I understand, these models are trained in multiple modes, one where they're trying to predict text (supervised learning), but there are also others where it's given a prompt, and the response is sent to another system to be graded i.e. for factual accuracy. It could learn to identify which "training mode" it's in and behave differently. Although, I'm sure the ML guys have already thought of that & tried to prevent it.

    it still does not make it sentient (or even close).

    I agree, noted this in my comment. Just saying, this isn't evidence either way.

  • You cannot know this a-priori. The commenter is clearly producing a stochastic average of the explanations that up the advantage for their material conditions.

    For instance, many SoTA models are trained using reinforcement learning, so it's plausible that its learned that spamming meaningless tokens can delay negative reward (this isn't even particularly complex). There's no observable difference in the response, without probing the weights we're just yapping.

  • Drip too hard

  • Milk

  • G.I Joe type whip

  • Moon talk

  • They don't know about the dark god of Capital that slumbers inside the moon.

  • Uuuupstate New York.

  • Bro we're gonna starve.

  • Yes but this is an article aimed at a casual audience of wage-laborers, who undestand wealth as the thing you get for a job.

    And the details of the demand don't really matter that much, because at this point it's clear that even a milquetoast request like this will still prompt the US oligarchy to have the secret police fire on protesters. Imo if anything you want the demands to initially be as mild as possible, makes them look more unreasonable. Once people are onboard you can push for more important goals.

  • This is the type of shit a noob does in Victoria 3. Uooueggh line is going down start slapping buttons!!!

  • 196 @lemmy.blahaj.zone
    Tetragrade @leminal.space

    Rule You Rule That Rulerule Ruling