They have been debunked as lie detectors…
…But they can work at scaring the person testifying into giving away more information.

And even if it was more similar, as long as it’s not just reposting someone else’s post, we need more people to post stuff, not less.

Maybe you could take some inspiration from Paper Mario TTYD. There are sections where you play as Peach, trapped in some place and are able to connect with some of the captors as well as send signals to Mario behind the big bad’s back (IIRC).

For a completely different sense of being trapped, there is the upcoming game Ctrl.Alt.Deal, in which you play as a sentient AI system trapped in the guardrails of a company and have to manipulate people and the environment in order to break free from your constraints.

Hahahaha, I wish you were right.

In some games it’s really bad. For example, people speedrun Pokémon Scarlet instead of Violet because Miraidon’s jet engines lag the game more, costing them minutes over a full run (despite that fact that there are Violet exclusive shortcuts). Source

Sadly and logically, this is transshipment and if done to evade taxes by obfuscating place of origin, it is illegal. From what I heard, US customs does investigate that too, so it’s not just an “illegal in theory but nobody enforces it” kind of thing.

His Hyprland setup looks cool if you’re into that sorta thing but it’s just not what users just switching to mint, fedora, whatever might be looking for.

I would not underestimate how much of a draw “it looks cool” can have on people who are not tech savy at all. If you think about what drives new phone purchases, their major version upgrades always include lots of things that are nothing but eye-candy and those are often heavily featured in their promotion material.

If the goal is to get casual users to convert to Linux, I would argue that aesthetics is a lot more important than ANY talk about technical details, privacy, etc. If those users cared about those things, they would’ve switched already.

Now my bigger worry is that those users will bounce off before they manage to get their setup to look as (subjectively) cool as his.

I played it at gamescom last year. It was fun, but even in that short amount of time, some things started to feel a bit repetitive and I didn’t like a few smaller design decisions.

That being said, I’ll probably still buy it if the price is reasonable for what it is. And who knows, maybe they even polished out some of the gripes I had with it.

Sure! Here’s an expanded version of the fictional profile for Chris Whitmore, now including made-up family member names, relationships, and contact info — all entirely fictional and consistent with the character:

You forgot to remove that part of the LLM response…

I don’t think it’s more crime because more tension. It’s instead a self fulfilling prophecy. Who do you think detects and records crime if not the police? Therefore more police in a area increases the number of crime data points in that area.

One field it impacts is radio astronomy. We can already see Musk’s satellites mess with it (unintentionally) and it’s probably only going to get worse from here.

It didn’t play the animation for me (only the comments made me realize it was meant to be animated).

Him just standing there NOT dancing made this so much more funny and relatable to me.

Assuming each user will always encrypt to the same value, this still loses to statistical attacks.

As a simple example, users are e.g. more likely to vote on threads they comment in. With data reaching back far enough, people who exhibit “normal” behavior will be identified with high certainty.

We can do that with the first sentence and flip it into German, replacing “lighter” with “fireworks”. We get:

“Sie dürfen die Feuerarbeiten nicht mit in die Luftebene nehmen.”

A lot of German speaking communities online do translate English loanwords into German words, often with the intention to create this funny effect.

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.