CloverSi @ CloverSi @lemmy.comfysnug.space

Posts

1

Comments

165

Joined

2 yr. ago

I usually let it do what it wants more, in the interest of good looking outputs. For more complex things I use a combination of the things you describe - prompt and controlnet tweaks - and img2img. You can let the original generation be ugly and overbaked, but as long as it has the right composition, you can then send it through img2img with a reduced prompt based more around style than composition. Or if you're really having the trouble getting the composition you want, you can even make a sketch or rough edit of it, then run that through img2img.

You're probably aware but it's worth mentioning: CFG scale and the model you use have a huge impact on overbaking (i.e. the ugly over+contrasted look with weird artifacts that happens when there's too detailed of a prompt). Any model trained to do something in particular will be much more prone to this; Deliberate v2 is my preferred model for how flexible it is, it takes a lot to get overbaked outputs. Also, lowering the CFG reduces overbaking risk a lot, and while it does add more 'randomness' it can sometimes be worth it. All about balancing it with your prompt.

I think the point they were making was that someone whose home, safety, or means of income were damaged or destroyed would have a different perspective than someone who wasn't adversely affected, regardless of the big picture.

Beautifully put my friend. If you ever run for office you have my vote.

Great analysis! Once again I see it differently but it's always cool to hear other perspectives.

I would agree that the protagonist's journey is often a primary part of a good film, but it's far from always the primary part of a good film. To me Evelyn and her arc filled a role closer to Nick(?) in The Great Gatsby, or Will Turner in Pirates of the Caribbean, or whats-his-face (the main guy, not Fred Rogers) from A Beautiful Day in the Neighborhood. They're the focal point of the story and are what drive it forward, but even though they have the most screentime the most interesting thing about them is their interaction with a 'side' character as a foil. While everything you describe regarding Evelyn and trying to support someone you care about are undoubtedly significant parts of the movie, they're not what make the movie stand out to me, and not what I would use to describe the 'point' of it.

Like you said, Joy and Evelyn wrestling with similar issues creates a great dynamic, where each offer different perspectives and challenges to the other. Where it sounds like you found Joy and her role in the movie to be more of a support in the main story of Evelyn's journey, to me Evelyn's side of things was more the lens through which to view the central story of the everything bagel. I see Evelyn's progression as being metaphor for how depression and nihilism creep in. Every part of her journey is another way you keep trying to fight it off, either internally or as help from loved ones, but things keep escalating no matter what you do until you end up at the bagel. The everything bagel's appearance and the Joy/Jobu reveal is the realization of what's been happening. From there it's less about the characters and more just the fundamental fight between the parts of us that can see a way of existing in the world and the parts of us that can't, whether those parts come from within or from loved ones.

To be clear I'm not trying to imply what you wrote is wrong in any way; I just thought it was interesting how, if I was asked to describe the movie's point, I would have given an answer more about the overall story and bagel-adjacent stuff than Evelyn's character arc. Our own experiences with the subject matter of the movie no doubt color our interpretations of what parts seem more 'important' than others. We can both be right :)

They're about as good as you could expect from a major cloud storage provider. In theory the encryption means that Mega can't access your files, but they're expressly very cooperative with government agencies so don't bet on anything you put there being entirely secure. I haven't heard of any major problems with them though - it's what I've been using for cloud storage the past few years and I haven't had an issue. As long as files aren't shared and therefor at risk of being reported there's not much to worry about, though in the case of things getting reported it's a 'take down first, ask questions later' type deal.

Here's a transparency report from them (how much to trust it is up to you): https://blog.mega.io/mega-transparency-report-2021/

That's beautiful, thanks for sharing. People like you and the judge, who will go against the grain to do the right thing, are what let me hope that we as a species might someday be able to get our shit together.

Thanks for making it a nicer place for everyone!

Interesting, my main takeaways aren't quite the same as yours! I can see what you describe too, but I would have summarized it very differently. I didn't see Evelyn's character growth and internal acceptance as a primary part of the film so much as a necessary story step in becoming the philosophical foil of Joy. I'm guessing Joy's arc is what you mean by the other really heavy point.

One thing I've noticed with this movie is that people experience it in very different ways, it resonates with a lot of people but there's a lot of variation in what exactly they get from it and how they interpret its message. It's really impressive how they were able to make it as universally enjoyable as they did, bringing together so many different themes coherently.

Now that I've lived near the ocean for a few years I think I'd be pretty bummed living somewhere away from the coast, but it seems like everyone's realizing how nice it is lol. At this point I'm not opposed to leaving the US if all the chill places with low cost of living keep disappearing here.

I need to get up at like four tomorrow so I'm gonna smoke a bit and try to get some sleep, gnight man!

Yeah, I know I'm really in no place to complain considering I'm a transplant too, but even in just the few years I've been here I've seen the changes. Apartments where there used to be a neighborhood, down to earth local businesses closing to make way for generic northeast-esque city stuff. I moved here with my family when I was still in high school, and I like it, but I'm pretty settled on leaving before I settle down here permanently. Hard to say where to though.

Lmao you're not wrong, though I'm surprised you're still alive - and a little impressed. You've been around here a while, what do you think of the area now compared to then? I haven't been here long.

That does sound fun. I used to live real close to downtown, within staggering distance, though sadly I'm a bit too far west for that now.

I like him, didn't know he was in town. Sucks that it rained but at least there was rain lol, my plants are only barely recovering from the drought. Much better than earlier this year but still pretty dang dry.

Oh I think I've walked by there, it's next to that bar with the rooftop patio right? Who'd you see?

That's awesome! I haven't been to any in the area yet. What kind of music you like?

Oh neat, I'm over in St Pete. Hey neighbor o/

!asklemmy@lemmy.world has been pretty busy today, thousands of comments in the last 24 hours.

I don't know much about how any of this works, but my guess would be the embedded browser on Connect hasn't been set up to block tracking? In which case you might try enabling the 'open links in external browser' option and see if you still get tracking attempts.

Well put! I think I kinda misunderstood what you were saying, I guess we sort of reached the same conclusion from different directions. And yeah, it does seem like we're hitting the limits of what can be achieved from the current underlying word-prediction mechanisms alone, with how diminishing the returns are from dumping more data in. Maybe something big will happen soon, but it looks to me like LLMs will stagnate for a while until they're taken in a fundamentally new direction.

Either way, what they can do now is pretty incredible, and equally interesting to me is how it's making us reevaluate our ideas of consciousness and intelligence on a large scale; it's one thing to theorize about what could happen with an 'intelligent' AI, but the reality of these philosophical questions being so thoroughly challenged and dissected in mundane legal and practical matters is wild.

My perspective is that consciousness isn't a binary thing, or even a linear scale. It's an amalgamation of a bunch of different independent processes working together; and how much each matters is entirely dependent on culture and beliefs. We're artificially creating these independent processes piece by piece in a way that doesn't line up with traditional ideas of consciousness. Conversation and being able to talk about concepts one hasn't personally experienced are facets of consciousness and intelligence, ones that the latest and greatest LLMs do have. Of course there others too that they don't: logic, physical presence, being able to imagine things in their mind's eye, memory, etc.

It's reductive to dismiss GPT4 as nothing more than mimicry; saying it's just a mathematical text prediction model is like saying your brain is just a bunch of neurons. Both statements are true, but it doesn't change what they can do. If someone could accurately predict the moves a chess master would make, we wouldn't say they're just good at statistics, we'd say they're a chess master. Similarly, regardless of how rich someone's internal world is, if they're unable to express the intelligent ideas they have in any intelligible way we wouldn't consider them intelligent.

So what we have now with AI are a few key parts of intelligence. One important thing to consider is how language can be a path to other types of intelligence; here's a blog post I stumbled across that really changed my perspective on that: http://www.asanai.net/2023/05/14/just-a-statistical-text-predictor/. Using your example of mathematics, as we know it falls apart doing anything remotely complicated. But when you help it approach the problem step-by-step in the way a human might - breaking it into small pieces and dealing with them one at a time - it actually does really well. Granted, the usefulness of this is limited when calculators exist and it requires as much guidance as a child to get correct answers, but even matching the mathematical intelligence of a ten year old is nothing to sneeze at.

To be clear I don't think pursuing LLMs endlessly will be the key to a widely accepted 'general intelligence'; it'll require a multitude of different processes and approaches working together for that to ever happen, and we're a long way from that. But it's also not just getting carried away with the hype to say the past few years have yielded massive steps towards 'true' artificial intelligence, and that current LLMs have enough use cases to change a lot of people's lives in very real ways (good or bad).