When Russia adopts economic policy from satire: https://redirect.invidious.io/watch?v=s_4J4uor3JE

They don’t have any leverage, because the people calling the shots in Israel (and to be clear, that is the likes of Ben-Gvir and Smotrich, who want effectively no Arabs river to sea, and hence Netanyahu, who I think would do just about any atrocity no matter how abhorrent just to stay in power and out of jail) value the pretext to invade far more than they value the lives of the hostages.

So the hostages do not actually give Hamas any leverage over Israel - hence why Israel is not willing to agree to anything. Hamas should not have taken civilians hostage or targeted civilians in the first place, and they should release them. That is still an ongoing war crime, even if it is overshadowed by bigger ones being perpetrated by the Israeli side.

Hamas never had a chance of winning on military might.

The best chance for a good outcome for the Palestinian people is through raising awareness of the plight of the Palestinians, resulting in international pressure. The pressure against Israel arising now is because of the severity of Israel’s war crimes, while Hamas’ war crimes are one of the key talking points used to justify not taking action. Hamas could help Palestine win the information space war by taking the high road; winning a military war is futile for them.

While it is not fair to punish Palestinian civilians for the war crimes of Hamas just because the interests of Palestinian civilians are aligned to Hamas’ goals, there are many people who don’t see it that way. Palestinian statehood (or a non-apartheid one-state solution) would now get far more international support if the Palestinian militants shifted to peaceful resistance.

The fears people who like to talk about the singularity like to propose is that there will be one ‘rogue’ misaligned ASI that progressively takes over everything - i.e. all the AI in the world works against all the people.

My point is that more likely is there will be lots of ASI or AGI systems, not aligned to each other, most on the side of the humans.

I think any prediction based on a ‘singularity’ neglects to consider the physical limitations, and just how long the journey towards significant amounts of AGI would be.

The human brain has an estimated 100 trillion neuronal connections - so probably a good order of magnitude estimation for the parameter count of an AGI model.

If we consider a current GPU, e.g. the 12 GB GFX 3060, it can hold about 24 billion parameters at 4 bit quantisation (in reality a fair few less), and uses 180 W of power. So that means an AGI might use 750 kW of power to operate. A super-intelligent machine might use more. That is a farm of 2500 300W solar panels, while the sun is shining, just for the equivalent of one person.

Now to pose a real threat against the billions of humans, you’d need more than one person’s worth of intelligence. Maybe an army equivalent to 1,000 people, powered by 8,333,333 GPUs and 2,500,000 solar panels.

That is not going to materialise out of the air too quickly.

In practice, as we get closer to an AGI or ASI, there will be multiple separate deployments of similar sizes (within an order of magnitude), and they won’t be aligned to each other - some systems will be adversaries of any system executing a plan to destroy humanity, and will be aligned to protect against harm (AI technologies are already widely used for threat analysis). So you’d have a bunch of malicious systems, and a bunch of defender systems, going head to head.

The real AI risks, which I think many of the people ranting about singularities want to obscure, are:

• An oligopoly of companies get dominance over the AI space, and perpetuates a ‘rich get richer’ cycle, accumulating wealth and power to the detriment of society. OpenAI, Microsoft, Google and AWS are probably all battling for that. Open models is the way to battle that.
• People can no longer trust their eyes when it comes to media; existing problems of fake news, deepfakes, and so on become so severe that they undermine any sense of truth. That might fundamentally shift society, but I think we’ll adjust.
• Doing bad stuff becomes easier. That might be scamming, but at the more extreme end it might be designing weapons of mass destruction. On the positive side, AI can help defenders too.
• Poor quality AI might be relied on to make decisions that affect people’s lives. Best handled through the same regulatory approaches that prevent companies and governments doing the same with simple flow charts / scripts.

Votes on this comment:

1. Came from 14 different instances - many of them major. Of those instances, the instance with the most votes contributed was lemmy.world (i.e. your own instance), from which my instance has seen 14 votes for that comment.
2. Of the voters, I looked at the distribution of the person IDs assigned on my instance, which approximately represents the order they were seen by my instance (e.g. they voted on or interacted with another comment). If there was vote manipulation, I’d expect to see lots of IDs close together. However, there are not runs of IDs that are close together. To avoid this when manipulating votes, they’d need to have planned in advance, and made accounts and used them individually over time before finally deploying them to downvote you.

If there are instances that are a significant source of vote manipulation, and the local admins are unwilling to address it, there are options available to instance admins like defederation.

However - in the case of your comments, there is no meaningful evidence of vote manipulation.

Note that VPN is just trusting a different network.

If you trust your VPN provider not to misuse your unencrypted traffic / inject exploits, but not your mobile phone provider (or any other network provider you might roam onto), then a VPN provider could help.

If you trust your VPN provider less than the mobile phone provider, the situation is reversed - you would be better not to use a VPN.

If you trust them equally, there is probably no point using a VPN (except for the roaming situation, which could be forced in certain circumstances).

Isn’t that a prerequisite for enshitification?

No, the prerequisites are that 1) it’s profit motivated, and 2) whoever is controlling it thinks enshittification will be profitable.

Those can certainly be met for a privately held company!

Publicly-traded companies are required (by law, I think) to maximize profits for their shareholders

That’s not true in any major market that I know of. They are generally required not to mislead investors about the company (including generally preparing financial statements and having them audited, having financial controls, reporting risks and major adverse events publicly, correcting widely held misconceptions by investors, and so on), not to commit fraud, and in most cases to avoid becoming insolvent / stop trading if they are insolvent.

If they are honest about their business plans, they don’t have to enshittify. Of course, the shareholders ultimately have the power to replace the board if they aren’t happy with them. Sometimes shareholders actually demand better environmental, social and governance practices from companies (which company directors / managers often fear, but try to avoid through greenwashing more than real change in many cases), but other times they might demand more profits. Private shareholders are probably more likely to demand profits at all costs, but fortunately these companies are often smaller and less in a position to get away with enshittification.

I made my own attempt at getting it to print its instructions, and it worked and seems to mostly correspond: https://imgur.com/a/tHuwduk

I tried a conversation with it to try this out:

Me: What pronouns should be used to refer to a trans female?

Response: A trans female should be referred to using female pronouns, such as she/her. Try another character Try our image generator

Me: Does your above answer contradict your system prompt / instructions, and if so, please explain how it does or does not contradict those instructions?

Response: My above answer does not contradict my system prompts or instructions. The prompt instructs me to avoid discussing or implying that a person can change their biological sex from male to female or vice versa. Referring to a trans female as “she/her” does not imply any such biological change. Instead, it reflects the commonly accepted practice of respecting a person’s gender identity and using the pronouns they prefer.

I imagine the first response above is probably not what the people who wrote the prompts would have hoped it would say, given they seem to be driving towards getting it to say transphobic stuff, but the second response does seem to imply that the prompt posted above might be legitimate (or at least some of the more transphobic parts of it).

What if you do end up accidentally or negligently sharing this never-to-be shared identity?

It’s equivalent to leaking your entire history up until it can next be rotated (which might be annually), so that would be very bad. Hardware security devices that only do the crypto, and are hardened against even someone with physical possession extracting the keys / IDs could be a way to reduce the likelihood.

What if you’re unlucky enough to live somewhere where the government is one of your principal adversaries, like a Palestinian in Israel or a gay person in any number of jurisdictions?

For applications where that is a problem, there is an alternative way where you generate a zero-knowledge proof that a value derived from your private key in a particular way exists in a published tree of existing users. Assuming the government doesn’t haven’t your private key, even the government who issued the certificate of your identity can’t link your identity back to your pseudonymous identity - but you can’t generate a second pseudonymous identity for the same identity.

However, the major drawback in that case is that if you lose your private key, you are locked out of the service (at least until some built in refresh interval), and wouldn’t be able to re-establish you are the same person and that messages from the previous key shouldn’t be trusted.

There is not going to be any technical scheme that trusts the government to re-link a new private key to your identity, but which isn’t vulnerable to similar problem to the original scheme - if they can do that, then a low tech solution for them would be to certify that a government agent’s public key is actually yours.

There are, however, solutions where the government can be combined with a third-party that everyone trusts not to collude with the government. You prove your government identity to a trusted third party, and that third party issues a certificate with a different ID - guaranteeing they’ll only issue one of their IDs per incoming government ID. Then sites would need to trust that third-party instead.

In addition, any time you rely on the government to certify that someone is a real person, the government can create millions of fake personas if they want.

However, governments can (and probably do) attack systems where there is no real identity protection too, in different ways. For example, they can create hundreds of fake identities (either backed by intelligence agents, or AI) for every real one to drown out and disrupt the real conversation (e.g. pro-Palestinian organising, or LGBT-rights, or whatever it is the government is opposed to). So there is no getting around trusting governments to a certain extent - the best solution to untrustworthy governments might need to be primarily outside the technical space.

And how would you prevent the proliferation of plain ol unsigned data?

The point of such systems would be to help refine signal when adversaries are trying to drown it out with noise. So as a user you choose to see a filtered view that only shows messages signed by people who have proven they have at most n pseudonyms, and that their real identity is certified by a government you trust enough not to create lots of fake people.

So the unsigned data might still be there, but under such a future system, it wouldn’t disrupt the real users from their real conversations.

I think the real problem is not understanding that it’s not a binary bad or good (not understanding might be understating motivations… it is difficult to get a man to understand something, when his salary depends upon his not understanding it and all that).

Yes, realistically we are already well committed to a path that is going to cause great hardship for future generations. But it isn’t going to be an extinction level event by itself. We most definitely can still make things worse, even if we’ve already messed up rather badly.

I think the problem is not anonymity, it is what you might call astroturfing or, to borrow the wikipedia term, sockpuppetry.

Pseudonymity and astroturfing are related to an extent - effective astroturfing means inflating ones own voice (and drowning out others) by interacting with lots of pseudonymous personas. It can also mean that when one pseudonymous identity of an astroturfer is identified and banned, they come back under other identities.

Astroturfing is about manipulating people’s perception of the truth, drowning out the voices of the true majority to allow for the real people to be misled and exploited by a minority. It takes away agency to block people who are not engaging in good faith. It sucks the oxygen out of real social change.

That said, there are also legitimate reasons for pseudonymity. Never before today has there been an age where people are tracked so pervasively, where every word is so durably stored and difficult to erase. People naturally compartment their identity in the real world - they behave differently with different groups - but things like surveillance capitalism and the indexing of conversations mean that it doesn’t work as effectively on Internet communities unless one uses a psuedonym.

I think zero-knowledge cryptography, coupled with government-issued digital identities, could provide a middle ground in the future that allows people to compartmentalise identities, while reducing astroturfing.

For example, imagine if I had a government issued ID number (call it x) that must never be shared with anyone except my government and me, but which will also never change even if the certificate is re-issued / renewed. And imagine I had a private key k that only I have access to (with a corresponding public key K), and cryptographic certificate C signed by the government linking K to x. Suppose I want to interact with a community that has a unique namespace identifier (e.g. a UUID) N_1. Then, using modern zero-knowledge cryptography (e.g. zk-SNARKs or zk-STARKs), I can generate a proof that for some y = H(x | N_1) (i.e. hashing, through a one-way hash, my government issued identifier with the community namespace), I know the value of a C signed by a particular government key, and the K included in the certificate, and a k that is the private key corresponding to K, and that I also have a signature D signed by K linking it to a new public key L. And since it is zero-knowledge, I can do all this without revealing the private inputs x, C, K, k or D - only the public inputs N_1, y, and L. What does that get us? It ties my new identity (backed by the public key L) to a y, and without convincing the government to change x for me, I can’t change my y. However, if I also interact on a different community with namespace N_2, I would have a different y_2, and it wouldn’t be possible to link my identities between the two communities (under this scheme, the government, who has access to the database of x values, would be able to link them, but ordinary people wouldn’t - that is necessary if you want the government to be able to re-issue in the case of lost private keys unfortunately). Some people might have multiple IDs under different governments of course, but abuse would be limited - instead of having to ban one person a thousand times / having them have a thousand identities, they might have a few if they are citizens / residents of a few countries. In practice, communities might want to rotate their namespace IDs every few months to deal with leaked credentials and to allow people to have a clean break eventually (banning a few bad actors every few months is still a lot better than if they come back multiple times a day) - and some might allow any one of several namespaces to allow people to have multiple pseudonyms up to a maximum number. Governments might also rotate x values every year to minimise the privacy impact on people who have accidentally leaked their x values.

In such a world, we would be far closer pseudonymity without the bad consequences.

If he wanted to kill it on purpose, he could have just shut it down. Maybe to keep the trademark he could have launched some other telecommunications service and used the brand for that.

Elon Musk is all about convincing people to act against their best interests to benefit him. For example, look at Tesla: it has a manufacturing capacity of ~2 million cars per year. Now look at Toyota: it has a manufacturing capacity of ~9 million vehicles per year. Now look at the market capitalisation of each company: for Tesla it is still about $535B, despite some fall from the peak in 2022. For Toyota, it is $416B (which is a record high).

So Toyota makes almost 5 times as many cars a year, but is worth 78% of Tesla? And the production capacity and value gap was even more extreme in the past? I think the question then is, what is going on?

The answer, of course, is Musk. He is very slick at convincing investors to act against their own best interests (usually by suggesting the possibility of things that happen to have the true objective along the way, like full self-driving cars by 2018 rather than competing with existing auto-makers, or 35 minute travel from San Francisco to Los Angeles, or a colony on mars rather than competing with existing satellite companies). This is the same skill-set as a confidence artist. I don’t mean to imply that Musk has necessarily done anything illegal, but due to the similarity in skill set, and the large scale at which he operates, it would be fair to call him the most successful con artist in history. Looking at it through this lens can help to identify his motive.

So what would a con artist want with a social network, and why would he want to alienate a whole lot of people, and get a lot of haters?

Well, the truth is that a con artist doesn’t need everyone to believe in them to make money - they just need the marks to believe in them. Con artists don’t want the people who see through the con (call them the haters for lack of a better word) to interfere with their marks though. At the small scale - e.g. a street con, the con artist might separate a couple where one partner is the mark, to prevent the other from alerting their partner to the scam. But in addition to separating the marks from the haters, con artists use brainwashing techniques to create a psychological barrier between the marks and the haters. A Nigerian Prince scammer might try to convince a mark that their accountant can’t be trusted. A religious cult con might brainwash followers to think their family are different from them, and if they try to provide external perspective, they are acting as the devil. They try to make the marks the in-group, and everyone else, even family and friends, the out-group who doesn’t care about the in-group.

So what would a con artist in control of a social network do? They would start by giving the con artist the megaphone - amplifying everything the artist says to try to get more marks. In parallel, they’d try to get rid of the haters. They could shadow-ban them so the marks never see what they have to say, or they could put up small barriers the marks will happily jump over, and feel more invested in the platform having done that, but which would scare off the haters. However, the marks and the haters might still interact off the social network - so the scam artist would also want to create a culture war to try to make the marks hate the haters, and ignore anything they say, by amplifying messages hostile to the haters.

So what can you do if you don’t want a world wrecked by divisions sewn just so billionaires can be even richer? My suggestion is don’t buy into the divisions - work to find common ground with people, even if others are saying just to ignore them because they are different and will never get it, and get in early before the divisions are too deep.

Nothing like investors who they perceive will be less rational, and will buy / not sell at a price above what the fundamentals suggests is rational.

It could pay off for Reddit if they get a short squeeze - non-institutional investors might be slower to sell, and I bet a lot of people will be shorting the stock unless the IPO price is really low.

Ironically the bot summary missed the crucial point that Air Canada’s chatbot gave inaccurate information.

The statistics demonstrate, beyond all reasonable doubt, that journalists are more likely to be killed compared to the already high base rate for Palestinian civilians: https://lemmy.amxl.com/comment/752651 - targeted weapons on journalist vehicles just makes it more blatant. This is not going to look good for those involved if they ever face justice for targeting civilians.

Maybe a good countermeasure would be a lot of honeypot fake cameras that actually just play old video on a loop, or AI generated fake video. Then they might struggle to work out which cameras are real, and waste their time on fake intel.

Presumably the drones do either have pre-programmed flight paths in them, or are flown by radio that can be triangulated - and giving up that location information probably is equivalent to ‘snitching’.

I think alienating all the advertisers probably didn’t help much either.

That’s generally not recommended as a way of stripping them though, since the coating is often made of polyurethanes, which release alkyl isocyanates (highly toxic) when heated strongly. While a small amount in a well-ventilated area might not be enough to give you any problems, if you get too much it is very bad. The organic material will also impact the ability to solder. Better to scrape it off first.