Mirodir

Whcih makes sense when explained, but it seems like few hear that kind of comparison.

And then you bring up defederation and/or how instances can die at any time and you lose them again...

At least that's how it usually goes for me and trying to advertise Lemmy. Not really a fan of "microblogging" to begin with no matter the platform.

For sure, that's why my main accusation is them directing traffic to their bad article (could even be an attempt at getting search engines to associate their article with "android games 2024") and not the AI stuff. I just started with the AI accusation because it was funny to me when OP and you already talked about AI (in games).

AI or not, the post is poorly written and has little to no informative content.

I do agree with you though, some people through around AI accusations way too quickly. Especially when they spot mistakes. LLMs are very good at NOT making grammatical or syntactical mistakes in English. If anything, those mistakes are often a sign of authenticity.

What games use AI to enrich the user experience? Highly doubting that one.

Even more so, I highly suspect OP is written with anything but AI. Even if we give them the benefit of the doubt that they wrote it by hand, it's very suspicious that their article on mobile games in 2024 has a url that states they're about 2021 and mentions mostly games from back then. Using the Wayback Machine (I would never give them a click) reveals that it's (mostly) the same article over all those years with the year in the title updated and some layout changes to fit the layout of the website.

While I cannot say with near certainty that OP is written by AI, I do feel confident saying that this post exists solely to direct traffic to that shitty article.

It's not copyright, it's patents...

(I do also hope that they lose because ingame mechanics being patented is bullshit)

That data is also publicly available (of course), so a model could be trained on it. I'd love to say I'd doubt Google/YouTube would ever do that, but at this point nothing would surprise me.

I trained the generative models all from scratch. Pretrained models are not that helpful when it's important to accurately capture very domain specific features.

One of the classifiers I tried was based on zoobot with a custom head. Assuming the publications around zoobot are truthful, it was trained exclusively on similar data from a multitude of different sky surveys.

Does it? I worked on training a classifier and a generative model on freely available galaxy images taken by Hubble and labelled in a citizen science approach. Where's the theft?

Reading this comment gave me the idea to get Gemini's "opinion". Ironically, it turns out Google might've actually done better if they did that.

It's a bit of a weird article indeed. I also fully disagree with the author's notion that reading a VN is faster than watching the anime equivalent. And I say this as someone who enjoys reading VNs every now and then. If I wanted to optimize the story/spent minute ratio I would just watch an anime or even better, read a manga.

Overall I hope the article can push a few people who were on the fence to the try reading a VN to finally do so. I doubt it'll affect anyone who was not very interested already. Likewise it also won't do much for people who already took the plunge.

Also I think DDLC isn't a good starter VN at all. All the meta stuff will be lost on the reader and the time before the twist is a real slog that might easily turn people off VNs forever. I would argue the only reason it worked is because streamers had their chats pressure them into continuing and "normal people" had friends who told them the same.

There was a fan translation, so fans were able to "complete the series in English" for quite some years already.

While I was quite happy to see it fimally get an official English release, I kinda hate this article not even mentioning the fan translation in passing.

I didn't say that.

I expect it to be about as awful as Starfield. However, unlike Starfield (which didn't sell horrendously by any source I can find, just not great) it has incredible brand recognition behind it. I have no doubts it will sell based on that alone as long as it looks like Skyrim 2 at first glance.

Edit: right after posting I figured out how to formulate what else I wanted to say but couldn't find the correct words for: "Sadly profitability and quality don't always correlate."

5.5 years? No way they'll shut down this quickly. The next Elder Scrolls alone will carry them into 2030. (As much as I would enjoy you being right though...)