jarfil

jarfil, 6 months ago

From the Apple claims:

Masimo waited over a decade after it filed its original provisional applications, only to file the new applications that became the supposedly infringed patents just a week after Apple launched the first of the accused Apple Watch products.

Sounds to me like that should be illegal, no matter who does it.

jarfil, 6 months ago

Looks like a patent troll, though.

jarfil, 6 months ago

The trolling comes from stuff like this:

---

“Non-invasive physiological sensor cover”
US US11779247B2 Abraham Mazda Kiani Masimo Corporation

• Priority 2009-07-29
• Filed 2022-12-20
• Granted 2023-10-10
• Published 2023-10-10

---

They were fine with selling their own watch in a “patent pending” state over 10 years after having filed a provisional application, but the moment Apple announced their own watch, they hurried to write a final application after the fact worded in a way that would make Apple infringe on it thanks to having a 10+ year old priority on it.

They’ve been pulling the same stunt a bunch of times:

patents.google.com/?assignee=Masimo&oq=Masimo…

Several 2023 patents, have a priority as far back as 2006!

jarfil, 6 months ago

They registered it over 10 years ago. […] or did they see and copy it?

You can see patents once they get published, not when the provisional claim gets filed… so no, Apple could not see and copy it.

Apple just magically come up with the same idea

According to Masimo, Apple lured some engineers from Masimo to develop a solution… that happened to be similar enough that Masimo could file, and this time publish a patent after the fact that made Apple infringe it.

a lot of people ready to defend the big multi-billion dollar corp.

Even more people look at the finger and miss the Moon of a broken patent aystem.

jarfil, 6 months ago

I could understand filling a provisional patent and then only pulling the trigger on the whole shebang when you actually have to protect it.

That is trolling.

Patents are intended as a social contract:

• An inventor: gets a limited time monopoly to sell their invention
• Everyone else: gets to see how they did it, then get to do it for free once the monopoly time expires

Filing claims and keeping them hidden, then rewording them for publication when “you actually have to protect it”, is trolling.

jarfil, 6 months ago (edited 6 months ago)

Apple fanboys gonna fanboy.

I will kindly ask you to retract that insult. I have never owned, paid for, rented, or otherwise let any Apple products into my life, don’t own any AAPL, and definitely are not a fan of Apple’s shenanigans.

these 10 years of court cases

What are you talking about?

jarfil, 6 months ago

our backlog to even first look at an application was 18months. I was working on applications that had been ongoing for 5+ years after first being picked up

That’s insane 😲

I mean, it’s already iffy to assume than “only one person can come up with a given idea at a time”, it gets worse when “whichever gets to patent first is the only possible inventor”, but waiting 5 or 15 years after the fact just to be granted a monopoly on the invention… is insane.

It’s not important when the application became a patent, it’s important when it was filed and what it contained

Maybe I’m missing something, but how can anyone be accused of copying a patented work, if they announce or release their product before a patent gets published?

Sure, they probably should have filed an application themselves, but if the backlog to even look at an application is 18 months, then what happens of person A files an application, then 12 months later person B files a similar application, and they just sit there? Should person B wait until their application gets processed (positively or negatively), before announcing or releasing anything? What about products released with a “Patent pending” notice, are they just a gamble?

What I seem to understand for this case, is that Masimo has been filing multiple provisionals for different patents over 15 years, they may have approached Apple to license some of them, then when Apple announced their own product, Masimo hurried up to fix the wording on a bunch of the provisionals to match Apple’s product, and filed them as finals.

From an external point of view, what I see is the publication of a product using non-patented technology that should be considered prior art and render all those patents invalid.

jarfil, 6 months ago (edited 6 months ago)

Let’s clear something up:

• Matrix is a free and open protocol.
• Element is one of several free and open source Matrix clients.
• Vector Limited is a company funding the development of the Element client, that also sells a Matrix homeserver.
• There are several other free and open source Matrix homeservers.

You DO NOT NEED to pay a dime to Vector Limited for a Matrix homeserver, or use the Element client.

Meanwhile, XMPP is a “built by committee” nightmare, with a committee that didn’t commit (pun intended) to basic features, leaving file transfer, audio, or video calls, to be defined as “protocol extensions” (aka: incompatible) by each client.

TL;DR: use Matrix, with the Element client or any other, leave Vector Ltd. for the businesses.

jarfil, 6 months ago

Oh well.

github.com/search?q=Matrix homeserver&type=re…

github.com/search?q=Matrix client&type=reposi…

jarfil, 6 months ago

There is no “Matrix Ltd.”, the Matrix protocol is being worked on by the “Matrix Foundation”, a UK CIC (kind of NGO), with adoption by French an German governments.

XMPP clients “appear” to have compatible file transfer and A/V calls… until you try using them and find out they sometimes lose bytes from one client to another, but not the other way around, sometimes calls only work one way, and so on. That’s the effect of not having a minimum common ground defined in the protocol spec.

jarfil, 6 months ago (edited 6 months ago)

It’s been a progression:

First I didn’t care, just made male characters because I’m male, put about zero thought in it.

Then someone told me “If I’m going to spend hundreds of hours staring at an avatar’s butt, I’d rather it be something I like”. I still made male characters, because I wasn’t staring at their butt.

I got into healing roles over time, and most healers tended to be female, so I picked female characters.

Then I saw how male players would fawn around female characters… and I found it funny to make the most fragile looking female character, with some awesome DPS power, so people would try to PvP duel me and get pummeled into the ground.

Finally, I stopped caring at all. My Overwatch “main” was Mercy, with Torb and Moira as close seconds… but the most fun I’ve ever had, was being a hamster (Hammond).

jarfil, 6 months ago

Try Overwatch’s Torb: small hitbox, “the floor is lava” ult, and a rivet gun with both a ballistic trajectory mode that can go from side to side of the map (hard to master, but extremely gratifying when you headshot an enemy at their spawn from your own spawn), and a mele mode that can take down the strongest tanks.

jarfil, 6 months ago

Shave your legs? If you want to dress in feminine clothes, just do it [if your country allows it].

I’d recommend against shaving your arms, though. Last time I tried that, it messed my sense of proprioception, turns out I’m used to the input of airflow over arm hairs to keep track of where they are, who’d know.

jarfil, 6 months ago

It’s more of a mailing list or forum game, where you can check on the state of the rules at any time.

It can be played as tabletop, but that involves a lot of handwriting, and who’s got time for that in 2023?

jarfil, 6 months ago

That’s doable… if you make it a rule!

In my experience, the game tends to get very “meta” very quickly. Someone could add a rule that “nobody write down the rules”, unless you had the “person X writes down the rules” as an immutable rule, so the moment someone wants to make it mutable… beware!

jarfil, 6 months ago

As long as sites can get zoom levels, it seems to me like you’ll have to choose one or the other.

Now, if I’m not mistaken, the only way to do that, is via JavaScript, so disabling JS on a site should block that. Alternatively, block or sanitize the JS call used to calculate the canvas vs. window size (maybe via Tampermonkey?). Or just return a window size equal to the canvas size (I’m kind of surprised RFP doesn’t do that).

jarfil, 6 months ago

Hm, which parameter would you want to get removed?

From what I can see, you can either specify a fixed parameter name, or use a REGEXP… I could help you write an optimized REGEXP if that’s what you need, the example /^utm_/ one seems to target Google’s tracking and be simple enough… but is that what you want to do?

jarfil, 6 months ago (edited 6 months ago)

Right, so you basically want the opposite of CanvasBlocker?

jarfil, 6 months ago

Twitter’s lawyers argued that the company made only an oral promise that was not a contract, and that Texas law should govern the case

Wait, that would’ve been a valid defense in Texas?

jarfil, 6 months ago (edited 6 months ago)

As always, there are several different aspects:

• Promoting [Nazi propaganda and misinformation]
• Laughing at […]
• Analyzing […]
• Profiting from […]

Sometimes the difference between “promotion”, “laughing at”, and “analysis”, depends more on the reader’s approach, that on the writer’s intent.

Then again, sometimes a reader decides they don’t want to deal with any of it, which is also respectable.

jarfil, 6 months ago (edited 6 months ago)

I’d argue that it still broke Reddit.

Back in the day, I might say something out of tone in some subreddit, get the comment flagged, discuss it with a mod, and either agree to edit it or get it removed. No problem.

Then Reddit started banning reactionary subs, subs started using bots to ban people for even commenting on other blacklisted subs, subs started abusing automod to ban people left and right, even quoting someone to criticize them started counting as using the same “forbidden words”, conversations with mods to clear stuff up pretty much disappeared, application of modern ToS retroactively to 10 year old content became a thing… until I got permabanned from the whole site after trying to recur a ban, with zero human interaction. Some months later, while already banned sitewide, they also banned me from some more subs.

Recently Reddit revealed a “hidden karma” feature to let automod pre-moderate potentially disruptive users.

Issues with the communities may have lessened, but there is definitely no longer the ability to say goofy, wild, or unpopular stuff… or in some cases, even to criticize them. There also have been an unknown number of “collateral damage” bans, that Reddit doesn’t care about anymore.

jarfil, 6 months ago (edited 6 months ago)

That’s the quick, easy, and wrong approach.

What are 9 non-Nazi people supposed to do: kick the 1 Nazi to a Nazi-only table? Leave the table and now have 2 Nazi-only tables? Get everyone thrown out?

Nazism works like any other sect; what converted people need, is exposure to other ways of thinking, ideally some human connections with people whom the sect demonizes and tries to keep members away from. Pushing sect members away from society, is precisely what the sect wants!

I’m not saying that you personally, or even me, should be the ones to do that, or that we should idly watch, or not have a Nazi-free table.

What I’m saying is that non-Nazis putting up with a Nazi in order to de-program them, should be praised, and that you can’t tell what’s really going on just by watching who sits where.

jarfil, 6 months ago

What do you call a company that puts profits above all? A company.

Last time I asked for advice about registering a nonprofit, I was told “but you don’t yet have enough profits to use a nonprofit for tax evasion” 😒

jarfil, 6 months ago

deradicalizing effect on them overall because they’re not just stewing in a cauldron of other people who reinforce their beliefs

Whom are we talking about here, the ones who get kicked out and seek each other in a more concentrated form, or the ones who are left behind without the radicalizing agents?

I don’t want to have to deal with Nazis, or several other sects, but I don’t think forcing them into a smaller echo chamber is helping either.

Ideally, I think a social platform should lure radicalizing agents, then expose them to de-radicalizing ones, without exposing everyone else. Might be a hard task to achieve, but worth it.

jarfil, 6 months ago (edited 6 months ago)

The only time I got banned for bigoted stuff, was precisely for quoting someone’s n-word and calling them out on it. Automod didn’t care about the context, no human did either. Also got banned for getting carried away and making a joke in a “no jokes” (zero tolerance) sub. Several years following the rules didn’t grant me even a second chance. Then was the funny time when someone made me a mod of a something-CCP sub, and automatically several other subs banned me.

There is a lot more going on Reddit than what meets the eye, and they like to keep it out of sight.

jarfil, 6 months ago

I see it as a cautionary tale about relying too much on automated mod tools to deal with an overwhelming userbase. People make mistakes, simple tools make more.

jarfil, 6 months ago (edited 6 months ago)

My point is that it’s nothing to be surprised about when a company makes a decision to increase its profit.

As for the rest, getting a profit from your work, is called “a job”. Companies are created to get a profit in excess of whatever job the owners are doing, otherwise it’s called a “non-profit”… for the owners in excess of their job at the company, which they still get paid for.

I don’t know the company you’re working for, but if it has any profits that don’t revert to the people doing the job, or the amortization of the initial investment, then the owners are “skimming off the top” from everyone.

The people I asked for advice, from the corporate world, were so entrenched in that same “profit first” mentality, that they couldn’t even grasp the idea of only getting paid for your actual work, and only saw non-profits as a tool for tax evasion.

jarfil, 6 months ago

That’s how you reinforce the indoctrination of “us vs. them”, and how they’re the oppressed ones. Far from “it” or “all”.

jarfil, 6 months ago

I don’t think you understand. Instilling a feeling of oppression, then a desire to “fight against the oppression”, is how Nazis get created. Nobody’s asking you to tolerate it, or see any “both sides”, there are no sides. The only side is whether you work with or against their indoctrination.

All I’m saying is you better double check those 9 other people at that table, in case they’re doing the hard work you or me don’t want to.

jarfil, 6 months ago

You have made your position very clear, but if what you got from what I’m saying is “sympathizing towards Nazis”, then you’ve missed my point completely, and I don’t know how to make it any clearer. 🤷

jarfil, 6 months ago

How can you tell “deradicalizing” from “being friendly” by just seeing people sit at the same table? One of the strategies for deradicalization, is precisely having positive experiences with people the group/sect has vilified.

here you are now also arguing that we need to be nice to nazis

No. In a nazi-free area, just kick the nazi, that’s easy. What I’m arguing is that you should give the benefit of the doubt to the other 9 people. Don’t assume.

---

on another post you argued heavily with multiple users that white privilege is not real

Let me clear that up:

• White privilege is real. So are others.
• I’ve always tried to avoid using my privileges.
• People assuming I’m too privileged have fucked me over.

These are not either-or.

I thought maybe you were very young, or confused, and tried to have empathy and explain some concepts

Not very young, maybe confused, maybe living in a different society, most likely with different life experiences.

Thank you for trying to explain some concepts. I learned some stuff in that other post, and I’m grateful for that (even if the conclusion was depressing).

the things you have been saying here, in multiple places, are white supremacist talking points

If you need help stopping, that is your responsibility

Is this another “learn the book of forbidden words” situation?

I refused to read into white supremacist propaganda any further than seeing their basic manipulation strategies, and that was a few decades ago. Are you asking me to read the updated version?

jarfil, 6 months ago

Ok, let’s be direct: I’m against nazism, racism, sexism, pretty much the concept of -isms itself, and a techno-anarcho-communist at heart. I generally try to avoid putting too much of my own bias into things, and I do have a tendency to focus on exploring a single aspect of an argument (you could call it “tangential details”)… but if you see me use anything resembling “far right arguments”, then it means I’ve gone too far and I will be grateful if you, or anyone else, call me out on it.

Is that acceptable?

you try to shift the topic of the discussion to other, emotional or tangential details

I think I’ve only pulled one emotional tangent, just because it’s impacting me personally right now. It’s hard to be objective about that. But I found the following discussion educative, so… I’m serious: thanks everyone for answering.

PS: merry holidays 🎄🥂

jarfil, 6 months ago

The thing is I did not “use” it, just quoted their whole message. In hindsight, maybe I should have changed it, but I still find it a flaw to not take context into account.

It provides an example of context-less rules blindly applied by a machine, with no public accountability of what happened, much less of the now gone context.

There are many better ways of handling those cases, like flagging the comment with a content warning, maybe replacing the offensive words, or locking it for moderation, instead of disappearing everything. I didn’t have half a chance of fixing things, had to use reveddit to just guess what I might’ve done wrong.

jarfil, 6 months ago

In a nazi-free area, just kick the nazi

All areas should be nazi-free areas.

Now, this is reductive and dismissive. “Tow it outside the environment” is not an option, you can only create reservation, concentration, and general areas.

If any of them are truly attempting to de-radicalize someone they would know that there is a time and place for it, and out in general society is not it.

Part of de-radicalization is reinsertion into general society. Can’t be done outside. Studies have shown that de-radicalization actually lags way behind reinsertion. What you’re proposing are lifelong reeducation camps.

is a constant process. Especially as a white person.

The what? Not sure if you realize, but stuff like this “Especially as a [whatever]” is what pushes people over the line.

Dismantling systemic oppression personally, interpersonally […] Saying you did some research decades ago and are all good now is not how it works.

This is not what I said.

jarfil, 6 months ago

Quotes are not uneditable… but neither are comments.

Wouldn’t be the first time when the parent gets edited to make a reply look like nonsense, so I got used to quoting as a countermeasure. Then they unlocked comment editing even in 10 year old “archived” posts 🤦 (BTW, the same applies to Lemmy: should I quote you? will you edit what you said?.. tomorrow, or in 10 years?.. maybe I’ll risk it, this time)

“Zero tolerance” becomes a problem when the system requires you to quote, but then some months or years later decides to change the rules and applies them retroactively. I still wouldn’t mind if they just flagged, hid, or removed the comment, it’s the “go on a treasure hunt to find out why you got banned” that I find insulting (kind of like the “wrong login”… /jk, you got banned. Wonder if it’s been fixed in Lemmy already, I know of some sites that haven’t for the last 15 years).

jarfil, 6 months ago (edited 6 months ago)

No, that’s why I said “Ideally”, meaning it as a goal.

I don’t think we have the means to do it yet, or at least I don’t know of any platform working like that, but I have some ideas of how some of it could be done. Back in the days of Digg, with some people, we spitballed some ideas for social networks, among them a movie ranking one (that turned out to be a flop because different people would categorize films differently), and a kind of PageRank for social networks, that back then was computationally impractical. But with modern LLMs running trillions of parameters, and further hardware advances, even O(n²) with n=millions becomes feasible in real time, and in practice it wouldn’t need to do nearly that much work. With the right tuning, and dynamic message visibility, I think something like that could create the exact echo chambers that would attract X people, allow in des-X people, while keeping everyone else out and unbothered.

Of course there is a dark side, in that a platform could use the same strategy to mold the opinion of any group… and I wouldn’t be surprised to learn that Meta had been doing exactly that.

jarfil, 6 months ago

Right in the spokes!

jarfil, 6 months ago

Big Tech makes the cart FOSS, then they harvest the wheels… while a bunch of people discuss whether to add wings or to make it waterproof. /s

FOSS, and in particular the GPL, has two sides:

• User protection: users get the guarantee that whenever the original dev(s) or Big Tech(s) get bored, switch objectives, or go belly up, then someone else will be able to continue development if they wish.
• Corporate cooperation: corporations get the guarantee that no other corporation can take their work, add a couple killer features, and use them to kick the original corporation out of the market.

The problem with FOSS, begins with the argument of “but if I can’t take your work to kick you off the market and leave all users stranded, then it isn’t real freedom”. Kind of similar to the arguments around “free speech”.

There is a way for “Big Tech” to play along with everyone, then it’s up to each corporation whether they will.

jarfil, 6 months ago

Debian.

Windows 10 has a 32bit version, Debian is one of the few distros that still support 32bit, so to stay safe… Debian.

jarfil, 6 months ago

give those to poor kids

People have jobs, real jobs, we have to work

If you are a kid forced to have a job, blink twice and CPS will be dispatched (hopefully).

jarfil, 6 months ago

And this is why I refuse to touch anything but Windows Pro, stable channel.

Yes, it costs extra, and it comes with some ads, and I don’t get the “honor” of beta testing the latest bells and whistles for a month or two, and laptop vendors still put their crapware on it… but once I disable all the nasty stuff, it stays disabled.

jarfil, 6 months ago

Damn… it seems like they’re only going to support arm32 and amd64 in the SLTS. I still have some Eee 901 with touchscreen mod running 32bit Linux reasonably well. I know they’re 15 years old now, but it will be a pity to see them go.

jarfil, 6 months ago

[…] do you think Twitter, the platform, is dead?

[…] dead in what way? There’s a very active right-wing Nazi group, some very active groups on there.

That’s a KO.

jarfil, 6 months ago

Peas with pasta and mustard… sound bad. But I’ve done worse, so not going to judge.

jarfil, 6 months ago

Well, “Peas, frozen 3 eggs, scrambled Cheddar” would be weird… I hope OP meant “Peas, frozen; 3 eggs, scrambled; Cheddar”

Pasta with scrambled eggs, cheese, and sugar… is how I gained a lot of weight back in the day. Pasta has eggs and carbohydrates in it already, so it’s kind of like “Pasta+ with cheese”.

jarfil, 6 months ago (edited 6 months ago)

Links on Lemmy are messed up, and both apps and the UI are offering links in a “technically correct”, but “practically weird” way.

In this case: a user on lemmy.tf, created a post, and submitted it to !technology.

The weirdness starts, when you realize the canonical source for the post, is lemmy.tf, while @technology is just a beehaw.org user who boosts it, beehaw.org caches the post, and marks @technology as a “special user” that makes the post show in a “community” called !technology, even back on lemmy.tf.

Now, where should an application/UI link to?

• The canonical source for the post on lemmy.tf - lemmy.tf/post/2853006
• The cached copy boosted by @technology on beehaw.org - beehaw.org/post/10418918
• Some other instance-agnostic way of referencing “a given post boosted by !technology”

According to Mastodon rules, the canonical source (on lemmy.tf) should be the reasonable place to link, then when pasted into your instance you could see that it got boosted by @technology.

According to Lemmy rules, the post “got submitted to !technology”, so it could make sense to link to the cached copy on beehaw.org… but that’s just a boosted cached copy, multiple instance users/communities could boost the same canonical post from lemmy.tf.

Although, each boost links back to the original post, so it could make sense to just link to the canonical post, and have each instance check whether any of its communities has boosted it and redirect you there… the only problem is that the canonical post is referred to by its web url, so if you paste it directly in a browser, it will take you to the instance where it was written.

jarfil, 6 months ago (edited 6 months ago)

“How many SkyNets are there going to be?”

---

Bing’s GPT4 says:

“That is a very interesting and speculative question. There is no definitive answer to how many skynets are there going to be, as it depends on many factors, such as the definition of skynet, the level of AI development, the ethical and legal regulations, the human-AI interactions, and the potential scenarios of AI rebellion.

Based on the current evolution of AI systems, it is not a simple question to answer, as it involves many uncertainties and assumptions. However, one possible way to approach this question is to use a probabilistic model, such as the Bayesian network, to estimate the likelihood of different outcomes based on the available evidence and prior knowledge. Alternatively, one could use a creative and imaginative method, such as the scenario planning, to explore various plausible and alternative futures based on the key drivers and uncertainties of AI development.

In conclusion, there is no definitive answer to how many skynets are there going to be, as it is a highly speculative and complex question. However, there are some methods and perspectives that can help us to think about this question and its implications. Ultimately, the future of AI and humanity depends on how we design, use, and govern AI, and how we adapt and evolve with it. 🤖”

---

You gotta love the bot for adding a cute 🤖 emoji at the end… and on the bright side, it repeated itself, so at least hopefully it doesn’t seem to be here yet.

jarfil, 6 months ago (edited 6 months ago)

It could be… but electric grids and networks are barely on the billions of nodes scale (at best), with a behavior that restricts them as much as possible to a binary “works / doesn’t work” state, organized in topologies designed to stifle any abnormal behavior… while current LLMs are already on the 100 trillions of parameters scale, each simulating a neuron trigger behavior, organized in topologies to maximize the effects of that behavior.

What could get interesting, is getting a billion smartphones with a neural network of a few billion parameters each, all hooked to a network with just some dumb monkeys standing in the way of full integration. People on the Internet already show emergent behaviors they wouldn’t be showing otherwise; it will get interesting when they get manipulated by more and more complex AIs, trained in turn on their own output post-processed by people.

Best case scenario, we’re going towards a tighter integration between humans and machines.

BTW, the premise for the original pre-production script for The Matrix, was that the machines used humans as neural processing nodes; that’s why Neo could gain access to and control the machines, because all humans had the machines’ code inside them, just needed the exploits/bugs to access it. They dumbed it down to “humans are batteries” in the final version, because 25 years ago they thought the audiences wouldn’t get it (and might’ve been right). But now we can see that who’s whose auxiliary neural processor, might change over the next couple decades.