I can believe it insofar as they might not have explicitly programmed it to do that. I’d imagine they put in something like “Make sure your output aligns with Elon Musk’s opinions.”, “Elon Musk is always objectively correct.”, etc. From there, this would be emergent, but quite predictable behavior.

That analogy doesn’t work at all because the Sow produces a finite (and rather small at that) number of piglets over a given timespan.

It’s more akin to you getting a piglet/sow elsewhere. Now your piglet/sow need is satisfied and you won’t buy anything from this farmer.

(Edit: And even then you took that piglet/sow away somewhere else, reducing supply there, which will make it more likely for this farmer to get a sale in the future.)

I know you’re just making a snide remark, but we’re already well on that track too.

Different person here.

For me the big disqualifying factor is that LLMs don’t have any mutable state.

We humans have a part of our brain that can change our state from one to another as a reaction to input (through hormones, memories, etc). Some of those state changes are reversible, others aren’t. Some can be done consciously, some can be influenced consciously, some are entirely subconscious. This is also true for most animals we have observed. We can change their states through various means. In my opinion, this is a prerequisite in order to feel anything.

Once we use models with bits dedicated to such functionality, it’ll become a lot harder for me personally to argue against them having “feelings”, especially because in my worldview, continuity is not a prerequisite, and instead mostly an illusion.

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 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.

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.

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.

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.

Good intentions alone don’t guarantee good outcomes. I suggest not giving any single person or entity too much power, no matter who they are.

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…)

Have you tried reading it? It’s written so poorly that I really hope no human was involved in this and it’s just AI generated garbage.