That’s a very optimistic view. Not licencing your patent to your competition is absolutely a profit driven decision that harms the end user.

There’s even a word for that called scurryfunging.

It was always meant to become a free game just like it’s predecessor. This is just that transition.

Labor of Love award is specifically for older games that are still seeing love from the devs. I’d argue with them releasing a DLC of such quality that many people wondered if a DLC could win game of the year it deserves the nomination too.

Re LLM summaries: I’ve noticed that too. For some of my classes shortly after the ChatGPT boom we were allowed to bring along summaries. I tried to feed it input text and told it to break it down into a sentence or two. Often it would just give a short summary about that topic but not actually use the concepts described in the original text.

Also minor nitpick but be wary of the term “accuracy”. It is a terrible metric for most use cases and when a company advertises their AI having a high accuracy they’re likely hiding something. For example, let’s say we wanted to develop a model that can detect cancer on medical images. If our test set consists of 1% cancer inages and 99% normal tissue the 99% accuracy is achieved trivially easy by a model just predicting “no cancer” every time. A lot of the more interesting problems have class imbalances far worse than this one too.

AI can be good but I’d argue letting an LLM autonomously write a paper is not one of the ways. The risk of it writing factually wrong things is just too great.

To give you an example from astronomy: AI can help filter out “uninteresting” data, which encompasses a large majority of data coming in. It can also help by removing noise from imaging and by drastically speeding up lengthy physical simulations, at the cost of some accuracy.

None of those use cases use LLMs though.

I wanna add to what other users already answered that this problem is not created by federation, only exacerbated.

If I’m mod of a community and I ban your Lost_My_Mind@lemmy.world account, I cannot stop you from creating, e.g. Lost_My_M1nd@lemmy.world and coming back. Most servers have some barriers against spam account creation in place, but I’d wager you could easily create a handful of accounts on a server until they start to grip.

Even completely centralized platforms such as Twitter and Reddit are the same. You can easily ban/block evade a couple times per timeframe.

Or a wrongly identified item…

My party (PF2E) had a spell scroll they completely misidentified as “Silence”. It was “Noise Blast”. They used it on a stealth mission…

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.

I haven’t looked into this game beyond your description, but it does sound like a pretty weird model. Do you also have to pay for cards on top of that?

It’s not a card game, it’s an async autobattler. As long as all the characters are roughly balanced against each other, there’s nothing to be gained other than cosmetics (at the current state of the game).

Don’t wanna be pedantic (yes I do) but after a little bit of searching, the originally presented quote seems correct (without the “and” though, it seems). Your version is mixed with a common misquote “Slowly at first, then all at once.” of that quote.

From experience with the beta and memory, your wife (and you) will be able to choose which version to play. Either yours with a ton of DLC or hers with none. You should both be able to use the version with all DLC, but not at the same time.

It’s been a while since we tested this though so things might have changed, including my memory…

after leaving can’t join another for a year

Can you fix this? There was enough misinformation floating around about this already when this feature went into beta.

Adults can leave a family at any time, however, they will need to wait 1 year from when they joined the previous family to create or join a new family.

it should say something like: “After joining, can’t join another for a year”

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.