GitHub are not some bastion of righteousness - they are literally owned by Microsoft. And they work hard to stop people from getting too much Open Source from them, with rate limits and the like, so essentially gate keep.

I think CSDN probably want to gatekeep their clone even harder, but in general having archives of GitHub on the Internet is a good thing.

Would you say its unfair to base pricing on any attribute of your customer/customer base?

A business being in a position to be able to implement differential pricing (at least beyond how they divide up their fixed costs) is a sign that something is unfair. The unfairness is not how they implement differential pricing, but that they can do it at all and still have customers.

YouTube can implement differential pricing because there is a power imbalance between them and consumers - if the consumers want access to a lot of content provided by people other than YouTube through YouTube, YouTube is in a position to say ‘take it or leave it’ about their prices, and consumers do not have another reasonable choice.

The reason they have this imbalance of market power and can implement differential pricing is because there are significant barriers to entry to compete with YouTube, preventing the emergence of a field of competitors. If anyone on the Internet could easily spin up a clone of YouTube, and charge lower prices for the equivalent service, competitors would pop up and undercut YouTube on pricing.

The biggest barrier is network effects - YouTube has the most users because they have the most content. They have the most content because people only upload it to them because they have the most users. So this becomes a cycle that helps YouTube and hinders competitors.

This is a classic case where regulators should step in. Imagine if large video providers were required to federated uploaded content on ActivityPub, and anyone could set up their own YouTube competitor with all the content. The price of the cheapest YouTube clones (which would have all the same content as YouTube) would quickly drop, and no one would have a reason to use YouTube.

would not be surprised if regional pricing is pretty much just above the break even mark

And in the efficient market, that’s how much the service would cost for everyone, because otherwise I could just go to a competitor of YouTube for less, and YouTube would have to lower their pricing to get customers, and so on until no one can lose their prices without losing money.

Unfortunately, efficient markets are just a neoliberal fantasy. In real life, there are network effects - YouTube has people uploading videos to it because it has the most viewers, and it has the most viewers because it has the most videos. It’s practically impossible for anyone to compete with them effectively because of this, and this is why they can put their prices in some regions up to get more profit. The proper solution is for regulators to step in and require things like data portability (e.g. requiring monopolists to publish videos they receive over open standards like ActivityPub), but regulatory capture makes that unlikely. In a just world, this would happen and their pricing would be close to the costs of running the platform.

So the people paying higher regional prices are paying money in a just world they shouldn’t have to pay, while those using VPNs to pay less are paying an amount closer to what it should be in a just world. That makes the VPN users people mitigating Google’s abuse, not abusers.

Yes, but for companies like Google, the vast majority of systems administration and SRE work is done over the Internet from wherever staff are, not by someone locally (excluding things like physical rack installation or pulling fibre, which is a minority of total effort). And generally the costs of bandwidth and installing hardware is higher in places with a smaller tech industry. For example, when Google on-sells their compute services through GCP (which are likely proportional to costs) they charge about 20% more for an n1-highcpu-2 instance in Mumbai than in Oregon, US.

that’s abuse of regional pricing

More like regional pricing is an attempt to maximise value extraction from consumers to best exploit their near monopoly. The abuse is by Google, and savvy consumers are working around the abuse, and then getting hit by more abuse from Google.

Regional pricing is done as a way to create differential pricing - all businesses dream of extracting more money from wealthy customers, while still being able to make a profit on less wealthy ones rather than driving them away with high prices. They find various ways to differentiate between wealthy and less wealthy (for example, if you come from a country with a higher average income, if you are using a User-Agent or fingerprint as coming from an expensive phone, and so on), and charge the wealthy more.

However, you can be assured that they are charging the people they’ve identified as less wealthy (e.g. in a low average income region) more than their marginal cost. Since YouTube is primarily going to be driven by marginal rather than fixed costs (it is very bandwidth and server heavy), and there is no reason to expect users in high-income locations cost YouTube more, it is a safe assumption that the gap between the regional prices is all extra profit.

High profits are a result of lack of competition - in a competitive market, they wouldn’t exist.

So all this comes full circle to Google exploiting a non-competitive market.

they have ran out of VC money

You know YouTube is owned by Google, not VC firms right?

Big companies sometimes keep a division / subsidiary less profitable for a time for a strategic reason, and then tighten the screws.

They generally only do this if they believe it will eventually be profitable over the long term (or support another part of the strategy so it is profitable overall). Otherwise they would have sold / shut it down earlier - the plan is always going to be to profitable.

However, while an unprofitable business always means either a plan to tighten screws, or to sell it / shut it down, tightening screws doesn’t mean it is unprofitable. They always want to be more profitable, even if they already are.

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.

I’m looking into it using data from my instance to check it isn’t an abuse issue.

What I know so far:

1. It is a lemmy.world user.
2. That user has downvoted 548 comments, and upvoted 18. Downvoted 557 posts and upvoted 25.
3. Timing: the downvoting has been going on for some time, it isn’t a new thing. 71 downvoted comments since 2024-06-01T00:00:00Z, 212 since the start of May (out of 548).
4. The user has two comments ever, and no posts. One comment, on a thread about the actions of a right-wing American politician, said “Click bait lemmy for sure”. This could imply the downvotes are legitimate and coming from having an impossibly high standard for what is considered quality here, or perhaps they are related to political grudges. I’m going to look further for patterns in the downvotes. I think a bot could have done far more downvotes - so it could just be a human.

I looked into this previously, and found that there is a major problem for most users in the Terms of Service at https://codeium.com/terms-of-service-individual.

Their agreement talks about “Autocomplete User Content” as meaning the context (i.e. the code you write, when you are using it to auto-complete, that the client sends to them) - so it is implied that this counts as “User Content”.

Then they have terms saying you licence them all your user content:

“By Posting User Content to or via the Service, you grant Exafunction a worldwide, non-exclusive, irrevocable, royalty-free, fully paid right and license (with the right to sublicense through multiple tiers) to host, store, reproduce, modify for the purpose of formatting for display and transfer User Content, as authorized in these Terms, in each instance whether now known or hereafter developed. You agree to pay all monies owing to any person or entity resulting from Posting your User Content and from Exafunction’s exercise of the license set forth in this Section.”

So in other words, let’s say you write a 1000 line piece of software, and release it under the GPL. Then you decide to trial Codeium, and autocomplete a few tiny things, sending your 1000 lines of code as context.

Then next week, a big corp wants to use your software in their closed source product, and don’t want to comply with the GPL. Exafunction can sell them a licence (“sublicence through multiple tiers”) to allow them to use the software you wrote without complying with the GPL. If it turns out that you used some GPLd code in your codebase (as the GPL allows), and the other developer sues Exafunction for violating the GPL, you have to pay any money owing.

I emailed them about this back in December, and they didn’t respond or change their terms - so they are aware that their terms allow this interpretation.

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.

I think the most striking thing is that for outsiders (i.e. non repo members) the acceptance rates for gendered are lower by a large and significant amount compared to non-gendered, regardless of the gender on Google+.

The definition of gendered basically means including the name or photo. In other words, putting your name and/or photo as your GitHub username is significantly correlated with decreased chances of a PR being merged as an outsider.

I suspect this definition of gendered also correlates heavily with other forms of discrimination. For example, name or photo likely also reveals ethnicity or skin colour in many cases. So an alternative hypothesis is that there is racism at play in deciding which PRs people, on average, accept. This would be a significant confounding factor with gender if the gender split of Open Source contributors is different by skin colour or ethnicity (which is plausible if there are different gender roles in different nations, and obviously different percentages of skin colour / ethnicity in different nations).

To really prove this is a gender effect they could do an experiment: assign participants to submit PRs either as a gendered or non-gendered profile, and measure the results. If that is too hard, an alternative for future research might be to at least try harder to compensate for confounding effects.

I think (unless I misunderstood the paper), they only included people who had a Google+ profile with a gender specified in the study at all (this is from 2016 when Google were still trying to make Google+ a thing).

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).

I think they’ll be useful for applications where the energy per unit of mass isn’t what matters. So not vehicles and not mobile devices - but there are still a huge range of applications left, especially in a world where we urgently need to move from fossil fuels to abundant but intermittent sources like solar and wind energy.

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).

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.