cross-posted from: https://lemmy.ml/post/5592397

> Forty years ago, Richard Stallman announced the plan to develop the GNU operating system, which would be entirely composed of free software. The existence of a free operating system would enable people to operate their computers in freedom, throwing off the power of the developers of nonfree software. The GNU Project has also built the global free software movement.

The app was not very good but it was pretty lightweight at least, and had no ads. Sad to see it go.

Now this YouTube Music Podcasts thing seems a bit off to me. It's not clear from the description if the podcasts are coming straight from RSS feeds like other, normal podcast players or if hosts have to upload them to the YouTube system.

If it's the former, I don't see why anybody would bother with the app since there are many adless alternatives to YouTube (podbean and antennapod are pretty neat), and at most Google would only get a little extra bit of interest data for said ads.

But if it's the latter this means that they are trying to do with podcasting what they did to music, attempting to consolidate a single big hub for it (regardless of whether the authors consent) and creating their own new chokepoint. A lot of people already post other people's podcasts on YouTube with dubious permission.

If successful, that'll be yet another medium completely enveloped by the Google ad industry. I would like to pretend people would be too angry at midroll ads in their history podcasts, but the boiled frog is mush at this point.

It's kinda funny because I just watched a Doctorow interview from a couple years back where he talked about this exact thing happening. Let's see how it plays out.

Edit: apparently it is direct uploads only, but Google promised it'll have RSS feeds next year. Might as well pirate all those shitty "2 bros talking" dead podcasts for some dollar.

cross-posted from: https://lemmy.ml/post/5486771

> We did an analysis of the Google antitrust trial. Last week, over half of the trial was held behind closed doors because the judge, Amit Mehta, is deferring to Google on the need for secrecy.

cross-posted from: https://lemmy.ml/post/5431344

> The enshittification of the internet follows a predictable trajectory: first, platforms are good to their users; then they abuse their users to make things better for their business customers; finally, they abuse those business customers to claw back all the value for themselves. Then, they die. It doesn't have to be this way. Enshittification occurs when companies gobble each other up in an orgy of mergers and acquisitions, reducing the internet to "five giant websites filled with screenshots of text from the other four" (credit to Tom Eastman!), which lets them endlessly tweak their back-ends to continue to shift value from users and business-customers to themselves. The government gets in on the act by banning tweaking by users - reverse-engineering, scraping, bots and other user-side self-help measures - leaving users helpless before the march of enshittification. We don't have to accept this! Disenshittifying the internet will require antitrust, limits on corporate tweaking - through privacy laws and other protections - and aggressive self-help measures from alternative app stores to ad blockers and beyond!

cross-posted from: https://lemmy.ml/post/5400607

> This is a classic case of tragedy of the commons, where a common resource is harmed by the profit interests of individuals. The traditional example of this is a public field that cattle can graze upon. Without any limits, individual cattle owners have an incentive to overgraze the land, destroying its value to everybody. > > We have commons on the internet, too. Despite all of its toxic corners, it is still full of vibrant portions that serve the public good — places like Wikipedia and Reddit forums, where volunteers often share knowledge in good faith and work hard to keep bad actors at bay. > > But these commons are now being overgrazed by rapacious tech companies that seek to feed all of the human wisdom, expertise, humor, anecdotes and advice they find in these places into their for-profit A.I. systems.

cross-posted from: https://lemmy.ml/post/5323962

> The Grift Shift is a new paradigm of debating technologies within a society that is based a lot less on the actual realistic use cases or properties of a certain technology but a surface level fascination with technologies but even more their narratives of future deliverance. Within the Grift Shift paradigm the topics and technologies addressed are mere material for public personalities to continuously claim expertise and “thought leadership” in every cycle of the shift regardless of what specific technologies are being talked about.

> 5.10 HiP:/ 当你们喷人家副业手机贵不如苹果的时候，人家的主业基站早都已经干到珠穆朗玛峰。# 华为 # 支持华为 # 5g # 华为珠穆朗玛基站  https://v.douyin.com/iemKQXto/ 复制此链接，打开Dou音搜索，直接观看视频！

5.10 HiP:/ When you criticize that their sideline mobile phones are not as expensive as Apple, their main base stations have already reached Mount Everest. # Huawei # Support Huawei # 5g # Huawei Everest Base Station https://v.douyin.com/iemKQXto/ Copy this link, open Douyin search, and watch the video directly!

Thoughts on this video?

I thought it was an interesting read. It's a very Pollyannish piece about the future where AI is somehow able to enable a workforce productivity revolution to save the American economy from its declining labor force.

But in the meantime they make the argument based on some quantitative economic work that in the last few years, growth in employment has slowed because automation is displacing many more workers than new jobs are being created from the automation. They even admit that this is mostly achieved by shoveling costs onto the consumer. The self-awareness is wild.

Happened a while ago but I didn't see people talking about it.

It'll even feature VS Code extensions so you can debug your copilot bugs you don't understand by posting generated prompts on Stack Overflow.

The video demonstration is also pretty funny, apparently CEOs think programmers don't know how to use search engines.

I've been looking into getting some freelance gig to help paying rent, but a lot of the websites look like those YouTube ad scams, promising "elite jobs" or other nonsense, and rely too much on building fake résumés. Stuff like Turing or even LinkedIn now. Anybody know any less terrible ones on an international level?

Due to personal reasons I can't really get a full-time job right now and don't even need that much money so low pay is alright for the time being so long as the workload is also low. I also don't have much "official" job experience, so "AI" CV readers will probably discard me really quickly despite me being in the field for a long time now.

Quite frankly, I never expected to see a fusion reactor became operational in our country for at least another decade. Such cooperation is practically unimaginable with any Western countries. The best we usually get is to take a few look at their own reactor, plus a few notes.

I might start a project to teach a couple of non-tech people how to work with computers at some point. I'd love to hook them up with Linux and libre/open office but the pragmatical reality is that they're gonna need the Windows know-how for employment reasons at least at first.

Problem with that is that Windows is expensive (only in hardware. who buys Microsoft software?). They're bloated and require progressively more advanced hardware to do the same thing they've done in the 90s. I'm trying to come up with ways to reduce costs to work with minimal hardware but my experience on that is only on the Linux front.

Does anybody have any experience with something like that, for example running some cracked Windows 7/XP, that could help?

I am hearing chatter that the ml domain has returned to Mali, which has an obvious impact on lemmygrad. Since lemmygrad is still working, is it not as big a deal as some are making it out to be?

I have this 11 year old oddly resistant Pentium laptop and I'm thinking of turning it into a reading/light-programming tool. It used to run great back in the day but modern software has gotten so bloated that it can barely run GNOME with Firefox, so I was thinking of sticking to command line only. Is there anything specific I should look into?

In specific I mainly only want to be able to download and read mdbooks in the terminal, probably using archlinux32 as the OS (or maybe LFS?). Captcha abuse and all that javascript already ruined browsing with Lynx so I have little hopes of actually browsing the web. I also intend to get a new battery as it only lasts 1-2 hours nowadays. Any other 32bit/tty-only customisation guides are also welcome.

cross-posted from: https://lemmygrad.ml/post/941245

> I have been interested in permaculture as well as ecologically sustainable computing, and I have finally found a community and concept that ties these two together. I was just browsing Gemini capsules (which you need a compatible web browser for), and I came across this: gemini://sol.cities.yesterweb.org/ > > Which led me to their http website: https://solflo.neocities.org/ > > On their about page, they recommend a permacomputing website here: https://compudanzas.net/permacomputing.html > > Which contained a link to the Permacomputing wiki (which this post directs to) and a web page from Ville-Matias "Viznut" Heikkilä that I am currently reading: http://viznut.fi/texts-en/permacomputing.html > > I hope this is a relevant community to share this. There's not really a permaculture, sustainability, or general computing (just realized there is a technology community, I will crosspost there) community on Lemmygrad that I could find at the moment, but I wanted to share this with my fellow comrades here.

Just another example of corporations attempting to co-opt instances of community building for eventual profit. So you know, capitalism.

I am unfortunately not very tech-savvy(I’m better at it than my parents lol but that’s not saying much) but I would like to know more(just a bit at a time, not like my friends in middle school who built their own PCs which is apparently kinda common among tech/gaming hobbyists with a bit of money but I was absolutely blown away). When I was in HS, there was the whole Ajit Pai thing and talk about Net Neutrality. It quickly blew over and people didn’t talk about it much. Basically TL;DR What is it? How does it differentiate from not having net neutrality and what are Marxist opinions on it?

Does Musk gain anything for making Mastodon such a good alternative?

I've always had issues with the modems provided by ISPs and the current one is acting up again. The discussions I've found on the internet are rather limited, and I couldn't parse if there are issues I should be aware of (like say, issues with the ISP or accidentally bricking the modem). Is there anything I should be aware of?

Given the amount of radical leftists using Lemmy, what's the risk that certain intelligence agencies create nice apps for Lemmy and put them on the app store to gather data on leftists?

It would be fairly cheap to do so.

I was looking for apps earlier today and noticed there's a bunch of new android apps for Lemmy and this thought occurred to me.

I feel this one is even more impactful for those of us who work in technology, as well as all other areas that have a lot of resources in SE like linguistics and physics. It seems like most people are not aware that it is going on and how important their demands are. Imagine working in software without Stack Overflow, or having it overrun by chatGPT "wrong but convincing" answers.

cross-posted from: https://lemmy.world/post/300452

> #### Prompt: > Please provide a brief summary of the current situation with Reddit and API access written in the style of "ELI5" - In addition, provide the 3 most likely outcomes and the % liklihood for each of the 3 to turn out. > > #### Response: > Okay, I'll try to explain it like you're five. Reddit is a website where people can post and comment on different topics. Some of these topics are called subreddits and they have their own rules and moderators. Moderators are people who help keep the subreddits clean and safe. > > Some people like to use other apps or websites to browse Reddit instead of the official one. These apps or websites need to talk to Reddit using a special language called API. API is like a phone line that lets them ask Reddit for information and send commands. For example, if you want to see the posts in r/aww using an app, the app will use API to ask Reddit to show you the cute pictures. > > Reddit used to let these apps or websites use API for free as long as they followed some rules and didn't make money from it. But recently, Reddit announced that they will start charging money for using API if the apps or websites make more than $1000 per month³⁴. This made some moderators very angry because they think Reddit is being greedy and unfair. They also think that this will hurt the users who like to use different apps or websites to enjoy Reddit. > > So some moderators decided to protest by making their subreddits go dark, which means that no one can see or post anything there³⁴. They hope that this will make Reddit change their mind and stop charging money for using API. They also want Reddit to listen to their feedback and improve their communication with the developers and moderators. > > The three most likely outcomes of this situation are: > > - Reddit backs down and cancels the API fees, or lowers them significantly. This might happen if the protest gets a lot of attention and support from the users and the media, and if Reddit realizes that they are losing traffic and reputation. The likelihood of this outcome is about 40%. > - Reddit sticks to their decision and enforces the API fees, or offers some compromises or incentives. This might happen if Reddit thinks that the protest is not effective enough or that they can afford to lose some users and subreddits. They might also try to appease the developers and moderators by giving them some benefits or discounts for using API. The likelihood of this outcome is about 50%. > - Reddit and the protesters reach a stalemate and nothing changes. This might happen if neither side is willing to budge or negotiate, and if the protest loses momentum or gets overshadowed by other events. The users might also get used to the new situation and adapt to it. The likelihood of this outcome is about 10%. > > I hope this helps you understand the current situation with Reddit and API access.

I bought a Positivo KaiOS dumbphone before the pandemic for outdoor use, but never got around to using it. I remember there being a lot of buzz around it being so cheap and jailbreaking it at the time to use FOSS apps, but I can't find anything recent on it. Is the project dead?

Guys, I create a community for nvidia. feel free to join. Thanks

https://lemmy.world/c/nvidia

https://lemmy.world/c/nvidia

[email protected]

The algorithm used for the cash relief program is broken, a Human Rights Watch report found.

A program spearheaded by the World Bank that uses algorithmic decision-making to means-test poverty relief money is failing the very people it’s intended to protect, according to a new report by Human Rights Watch. The anti-poverty program in question, known as the Unified Cash Transfer Program, was put in place by the Jordanian government.

Having software systems make important choices is often billed as a means of making those choices more rational, fair, and effective. In the case of the poverty relief program, however, the Human Rights Watch investigation found the algorithm relies on stereotypes and faulty assumptions about poverty.

“Its formula also flattens the economic complexity of people’s lives into a crude ranking.”

“The problem is not merely that the algorithm relies on inaccurate and unreliable data about people’s finances,” the report found. “Its formula also flattens the economic complexity of people’s lives into a crude ranking that pits one household against another, fueling social tension and perceptions of unfairness.” Join Our Newsletter Original reporting. Fearless journalism. Delivered to you. I'm in

The program, known in Jordan as Takaful, is meant to solve a real problem: The World Bank provided the Jordanian state with a multibillion-dollar poverty relief loan, but it’s impossible for the loan to cover all of Jordan’s needs.

Without enough cash to cut every needy Jordanian a check, Takaful works by analyzing the household income and expenses of every applicant, along with nearly 60 socioeconomic factors like electricity use, car ownership, business licenses, employment history, illness, and gender. These responses are then ranked — using a secret algorithm — to automatically determine who are the poorest and most deserving of relief. The idea is that such a sorting algorithm would direct cash to the most vulnerable Jordanians who are in most dire need of it. According to Human Rights Watch, the algorithm is broken.

The rights group’s investigation found that car ownership seems to be a disqualifying factor for many Takaful applicants, even if they are too poor to buy gas to drive the car.

Similarly, applicants are penalized for using electricity and water based on the presumption that their ability to afford utility payments is evidence that they are not as destitute as those who can’t. The Human Rights Watch report, however, explains that sometimes electricity usage is high precisely for poverty-related reasons. “For example, a 2020 study of housing sustainability in Amman found that almost 75 percent of low-to-middle income households surveyed lived in apartments with poor thermal insulation, making them more expensive to heat.”

In other cases, one Jordanian household may be using more electricity than their neighbors because they are stuck with old, energy-inefficient home appliances.

Beyond the technical problems with Takaful itself are the knock-on effects of digital means-testing. The report notes that many people in dire need of relief money lack the internet access to even apply for it, requiring them to find, or pay for, a ride to an internet café, where they are subject to further fees and charges to get online.

“Who needs money?” asked one 29-year-old Jordanian Takaful recipient who spoke to Human Rights Watch. “The people who really don’t know how [to apply] or don’t have internet or computer access.”

Human Rights Watch also faulted Takaful’s insistence that applicants’ self-reported income match up exactly with their self-reported household expenses, which “fails to recognize how people struggle to make ends meet, or their reliance on credit, support from family, and other ad hoc measures to bridge the gap.”

The report found that the rigidity of this step forced people to simply fudge the numbers so that their applications would even be processed, undermining the algorithm’s illusion of objectivity. “Forcing people to mold their hardships to fit the algorithm’s calculus of need,” the report said, “undermines Takaful’s targeting accuracy, and claims by the government and the World Bank that this is the most effective way to maximize limited resources.” Related AI Tries (and Fails) to Detect Weapons in Schools

The report, based on 70 interviews with Takaful applicants, Jordanian government workers, and World Bank personnel, emphasizes that the system is part of a broader trend by the World Bank to popularize algorithmically means-tested social benefits over universal programs throughout the developing economies in the so-called Global South.

Confounding the dysfunction of an algorithmic program like Takaful is the increasingly held naïve assumption that automated decision-making software is so sophisticated that its results are less likely to be faulty. Just as dazzled ChatGPT users often accept nonsense outputs from the chatbot because the concept of a convincing chatbot is so inherently impressive, artificial intelligence ethicists warn the veneer of automated intelligence surrounding automated welfare distribution leads to a similar myopia.

The Jordanian government’s official statement to Human Rights Watch defending Takaful’s underlying technology provides a perfect example: “The methodology categorizes poor households to 10 layers, starting from the poorest to the least poor, then each layer includes 100 sub-layers, using statistical analysis. Thus, resulting in 1,000 readings that differentiate amongst households’ unique welfare status and needs.”

“These are technical words that don’t make any sense together.”

When Human Rights Watch asked the Distributed AI Research Institute to review these remarks, Alex Hanna, the group’s director of research, concluded, “These are technical words that don’t make any sense together.” DAIR senior researcher Nyalleng Moorosi added, “I think they are using this language as technical obfuscation.”

As is the case with virtually all automated decision-making systems, while the people who designed Takaful insist on its fairness and functionality, they refuse to let anyone look under the hood. Though it’s known Takaful uses 57 different criteria to rank poorness, the report notes that the Jordanian National Aid Fund, which administers the system, “declined to disclose the full list of indicators and the specific weights assigned, saying that these were for internal purposes only and ‘constantly changing.’”

While fantastical visions of “Terminator”-like artificial intelligences have come to dominate public fears around automated decision-making, other technologists argue civil society ought to focus on real, current harms caused by systems like Takaful, not nightmare scenarios drawn from science fiction.

So long as the functionality of Takaful and its ilk remain government and corporate secrets, the extent of those risks will remain unknown.

Lots of the classical writing on property and capital are from a pre-software era, which doesn't make it wrong, but I see many things that are so extremely exacerbated with software that have been peeking my interest lately.

For instance, I'm not aware of any other profession in history that can, as the software companies themselves call it, "turn pizza into code". Such low costs to producing what is essentially brand new capital that requires marginal labour to operate are unprecedented AFAIK. If I were to speculate, that is exactly why software developers are so exalted in the capitalist media and market, even though a lot of their work is either useless or discarded (just look at google graveyard) despite their disproportional salaries. They literally turn food and electricity into intangible and scalable capital.

(I'm generally from the field, if it looks like I hold it against y'all lol)

Hi, I create a sub/community to discuss all VPN related without affiliated to specific brands. https://lemmy.world/c/vpn

HTTPS is becoming increasingly important for every website out there on the internet and even on intranet sites. As HTTPS prevents eavesdropping and MiTM attacks. All major browsers discourage visiting HTTP-only websites and there are multiple initiatives to issue TLS/SSL certificates needed for HTTPS to as many websites as possible..... except to websites based in US-sanctioned countries.

The prime example of excluded from the secure internet due to US sanctions is the DPRK. While the China-based DPRK website Uriminzokkiri has a valid TLS/SSL certificate, all DPRK-based websites such as Naenara, KCNA, Voice of Korea and Rodong Sinmun do not have access to any kind of TLS/SSL certificate.

What do we do? Try to take action via our US-based comrades? Try to start our own CA?

Hi Guys I create a new community related to Intel products. feel free to join https://lemmy.world/c/intel