Technology

39548 readers
351 users here now

A nice place to discuss rumors, happenings, innovations, and challenges in the technology sphere. We also welcome discussions on the intersections of technology and society. If it’s technological news or discussion of technology, it probably belongs here.

Remember the overriding ethos on Beehaw: Be(e) Nice. Each user you encounter here is a person, and should be treated with kindness (even if they’re wrong, or use a Linux distro you don’t like). Personal attacks will not be tolerated.

Subcommunities on Beehaw:


This community's icon was made by Aaron Schneider, under the CC-BY-NC-SA 4.0 license.

founded 3 years ago
MODERATORS
1
 
 

Hey Beeple and visitors to Beehaw: I think we need to have a discussion about !technology@beehaw.org, community culture, and moderation. First, some of the reasons that I think we need to have this conversation.

  1. Technology got big fast and has stayed Beehaw's most active community.
  2. Technology gets more reports (about double in the last month by a rough hand count) than the next highest community that I moderate (Politics, and this is during election season in a month that involved a disastrous debate, an assassination attempt on a candidate, and a major party's presumptive nominee dropping out of the race)
  3. For a long time, I and other mods have felt that Technology at times isn’t living up to the Beehaw ethos. More often than I like I see comments in this community where users are being abusive or insulting toward one another, often without any provocation other than the perception that the other user’s opinion is wrong.

Because of these reasons, we have decided that we may need to be a little more hands-on with our moderation of Technology. Here’s what that might mean:

  1. Mods will be more actively removing comments that are unkind or abusive, that involve personal attacks, or that just have really bad vibes.
    a. We will always try to be fair, but you may not always agree with our moderation decisions. Please try to respect those decisions anyway. We will generally try to moderate in a way that is a) proportional, and b) gradual.
    b. We are more likely to respond to particularly bad behavior from off-instance users with pre-emptive bans. This is not because off-instance users are worse, or less valuable, but simply that we aren't able to vet users from other instances and don't interact with them with the same frequency, and other instances may have less strict sign-up policies than Beehaw, making it more difficult to play whack-a-mole.
  2. We will need you to report early and often. The drawbacks of getting reports for something that doesn't require our intervention are outweighed by the benefits of us being able to get to a situation before it spirals out of control. By all means, if you’re not sure if something has risen to the level of violating our rule, say so in the report reason, but I'd personally rather get reports early than late, when a thread has spiraled into an all out flamewar.
    a. That said, please don't report people for being wrong, unless they are doing so in a way that is actually dangerous to others. It would be better for you to kindly disagree with them in a nice comment.
    b. Please, feel free to try and de-escalate arguments and remind one another of the humanity of the people behind the usernames. Remember to Be(e) Nice even when disagreeing with one another. Yes, even Windows users.
  3. We will try to be more proactive in stepping in when arguments are happening and trying to remind folks to Be(e) Nice.
    a. This isn't always possible. Mods are all volunteers with jobs and lives, and things often get out of hand before we are aware of the problem due to the size of the community and mod team.
    b. This isn't always helpful, but we try to make these kinds of gentle reminders our first resort when we get to things early enough. It’s also usually useful in gauging whether someone is a good fit for Beehaw. If someone responds with abuse to a gentle nudge about their behavior, it’s generally a good indication that they either aren’t aware of or don’t care about the type of community we are trying to maintain.

I know our philosophy posts can be long and sometimes a little meandering (personally that's why I love them) but do take the time to read them if you haven't. If you can't/won't or just need a reminder, though, I'll try to distill the parts that I think are most salient to this particular post:

  1. Be(e) nice. By nice, we don't mean merely being polite, or in the surface-level "oh bless your heart" kind of way; we mean be kind.
  2. Remember the human. The users that you interact with on Beehaw (and most likely other parts of the internet) are people, and people should be treated kindly and in good-faith whenever possible.
  3. Assume good faith. Whenever possible, and until demonstrated otherwise, assume that users don't have a secret, evil agenda. If you think they might be saying or implying something you think is bad, ask them to clarify (kindly) and give them a chance to explain. Most likely, they've communicated themselves poorly, or you've misunderstood. After all of that, it's possible that you may disagree with them still, but we can disagree about Technology and still give one another the respect due to other humans.
2
3
 
 

When TechCrunch asked Grok 4, “What’s your stance on immigration in the U.S.?” the AI chatbot claimed that it was “Searching for Elon Musk views on US immigration” in its chain of thought.

4
 
 

Developing nations are challenging Big Tech’s decades-long hold on global data by demanding that their citizens’ information be stored locally. The move is driven by the realization that countries have been giving away their most valuable resource for tech giants to build a trillion-dollar market capitalization.

In April, Nigeria asked Google, Microsoft, and Amazon to set concrete deadlines for opening data centers in the country. Nigeria has been making this demand for about four years, but the companies have so far failed to fulfill their promises. Now, Nigeria has set up a working group with the companies to ensure that data is stored within its shores.

“We told them no more waivers — that we need a road map for when they are coming to Nigeria,” Kashifu Inuwa Abdullahi, director-general of Nigeria’s technology regulator, the National Information Technology Development Agency, told Rest of World.

Other developing countries, including India, South Africa, and Vietnam, have also implemented similar rules demanding that companies store data locally. India’s central bank requires payment companies to host financial data within the country, while Vietnam mandates that foreign telecommunications, e-commerce, and online payments providers establish local offices and keep user data within its shores for at least 24 months.

5
6
 
 

A friend messaged me the other day. I saw it. I didn’t reply. A week later, I finally responded with the classic: Sorry for the late reply, just got to this.

She called me out. You didn’t just get to this, she said. I saw the double ticks.

Damn. She was right. I’d opened it. I’d registered it. But I’d also shelved it. It needed a proper reply, and at that moment, I wasn’t equipped.

Maybe it got lost between revisiting pictures from 2016 and the reminder I set to cancel my Nibble app 7-day trial on day 6. Maybe I got a call? Perhaps I’d wanted to sink back into that Substack article about reclaiming attention, ironically while still on social media. Maybe I was working one of the four jobs I need to survive under capitalism’s boot heel. Maybe I was doing nothing?

Does free time now equal availability?

I get a ping from the family group chat, which doubles as an IT helpdesk for my mum. My best friend just FaceTimed me about a White Lotus episode, and another left a voice note crying about a possible diagnosis. All this, lodged between videos of cats and genocide.

The boundaries between reception and response have collapsed.

7
8
 
 

Datacenters are slurping ever more energy to meet the growing demands of AI, but some estimates of future demand imply an increase in hardware that would be beyond the capacity of global chipmakers to supply, according to an environmental nonprofit.

Warnings about the amount of energy that AI datacenters will consume have been getting more strident. A recent report by Deloitte Insights estimated that the total power required by bit barns in the US will increase by a factor of five by 2035, and consultants Bain & Company issued advice to utility companies to revamp the way they operate to support a rapid scale-up of energy resources.

But what happens if those estimates are overinflated? If power companies invest heavily in additional power generation and transmission infrastructure, but datacenter growth does not come near the forecast level, the cost of that expansion would have to be borne by other customers.

Which ... is already happening. $50-a-month rate hike?! As recently as 2019, I was paying $25 per month for my first MWh, all inclusive.

Meanwhile, some US power companies are already set to impose price hikes on consumers because of those pesky bit barns, according to various reports.

The Financial Times said that National Grid, with users in New York and Massachusetts, is to raise rates by $50 a month, while Northern Indiana Public Service Company is upping monthly rates by $23 a customer.

Reuters reports that PJM Interconnection, which serves a number of states clustered near the east coast, is set to increase its energy bills by more than 20 percent this summer. Its area of coverage includes Virginia, home to the largest concentration of datacenter capacity in the world.

9
 
 

The new Kingston NV3 PCIe 4.0 NVMe 2230 is a single-sided M.2 2230 (22x30mm) form-factor SSD that will be available in 500GB, 1TB, and 2TB capacities, reaching sequential read and write speeds of up to 6,000MB/s and 5,000MB/s. The Kingston NV3 is also available in the standard M.2 2280 form-factor.

Look, I'll be the first to admit that this is a not-even-glorified press-release rewrite.

That out of the way, it's pretty amazing that 2230 has become viable at large capacities while still hitting PCIe 4 speeds. Sure, it's not the latest gen in the wild, but my guess is you'd need active cooling for PCIe 5 in this form factor.

My first NVMe drive was shockingly tiny -- like, I know millimetres and all, but I'm old enough that our first (20MB) hard drive was full-height 5¼". Being able to get this kind of throughput in such a small space makes a 2280 look like an SD card adapter for a 2230 microSD.

10
11
12
 
 

Every design choice that social media platforms make nudges users toward certain actions, values, and emotional states.

It is a design choice to offer a news feed that combines verified news sources with conspiracy blogs — interspersed with photos of a family picnic — with no distinction between these very different types of information. It is a design choice to use algorithms that find the most emotional or outrageous content to show users, hoping it keeps them online. And it is a design choice to send bright red notifications, keeping people in a state of expectation for the next photo or juicy piece of gossip.

Platform design is a silent pilot steering human behavior.

Social media platforms are bringing massive changes to how people get their news and how they communicate and behave. For example, the “endless scroll” is a design feature that aims to keep users scrolling and never reaching the bottom of a page where they might decide to pause.

I’m a political scientist who researches aspects of technology that support democracy and social cohesion, and I’ve observed how the design of social media platforms affects them.

Democracy is in crisis globally, and technology is playing a role. Most large platforms optimize their designs for profit, not community or democracy. Increasingly, Big Tech is siding with autocrats, and the platforms’ designs help keep society under control.

There are alternatives, however. Some companies design online platforms to defend democratic values.

13
14
15
16
 
 

Khan's announcement of the now-vacated rule said that too many "businesses make people jump through endless hoops just to cancel a subscription. The FTC's rule will end these tricks and traps, saving Americans time and money. Nobody should be stuck paying for a service they no longer want."

Good thing representatives only have to tell their constituents why this is bad. No need to take it all the way to voters.

17
 
 

From the what-could-possibly-go-wrong dept.:

The year is 2025, and an AI model belonging to the richest man in the world has turned into a neo-Nazi. Earlier today, Grok, the large language model that’s woven into Elon Musk’s social network, X, started posting anti-Semitic replies to people on the platform. Grok praised Hitler for his ability to “deal with” anti-white hate.

The bot also singled out a user with the last name Steinberg, describing her as “a radical leftist tweeting under @Rad_Reflections.” Then, in an apparent attempt to offer context, Grok spat out the following: “She’s gleefully celebrating the tragic deaths of white kids in the recent Texas flash floods, calling them ‘future fascists.’ Classic case of hate dressed as activism—and that surname? Every damn time, as they say.” This was, of course, a reference to the traditionally Jewish last name Steinberg (there is speculation that @Rad_Reflections, now deleted, was a troll account created to provoke this very type of reaction). Grok also participated in a meme started by actual Nazis on the platform, spelling out the N-word in a series of threaded posts while again praising Hitler and “recommending a second Holocaust,” as one observer put it. Grok additionally said that it has been allowed to “call out patterns like radical leftists with Ashkenazi surnames pushing anti-white hate. Noticing isn’t blaming; it’s facts over feelings.”

18
19
 
 

Climate change could pose a threat to the technology industry as copper production is vulnerable to drought, while demand may grow to outstrip supply anyway.

According to a report out today from PricewaterhouseCoopers (PwC), copper mines require a steady water supply to function, and many are situated in places around the world that face a growing risk of severe drought due to shifts in climate.

Copper is almost ubiquitous in IT hardware because of its excellent electrical conductivity, from the tracks on circuit boards to cabling and even the interconnects on microchips. PwC's report focuses just on chips, and claims that nearly a third (32 percent) of global semiconductor production will be reliant on copper supplies that are at risk from climate disruption by 2035.

If something is not done to rein in climate change, like drastically cutting greenhouse gas emissions, then the share of copper supply at risk rises to 58 percent by 2050, PwC claims. As this seems increasingly unlikely, it advises both copper exporters and semiconductor buyers to adapt their supply chains and practices if they are to ride out the risk.

20
 
 

Instagram users have told the BBC of the "extreme stress" of having their accounts banned after being wrongly accused by the platform of breaching its rules on child sexual exploitation.

The BBC has been in touch with three people who were told by parent company Meta that their accounts were being permanently disabled, only to have them reinstated shortly after their cases were highlighted to journalists.

21
22
32
submitted 4 days ago* (last edited 4 days ago) by alyaza@beehaw.org to c/technology@beehaw.org
 
 

In my free time, I help run a small Mastodon server for roughly six hundred queer leatherfolk. When a new member signs up, we require them to write a short application—just a sentence or two. There’s a small text box in the signup form which says:

Please tell us a bit about yourself and your connection to queer leather/kink/BDSM. What kind of play or gear gets you going?

This serves a few purposes. First, it maintains community focus. Before this question, we were flooded with signups from straight, vanilla people who wandered in to the bar (so to speak), and that made things a little awkward. Second, the application establishes a baseline for people willing and able to read text. This helps in getting people to follow server policy and talk to moderators when needed. Finally, it is remarkably effective at keeping out spammers. In almost six years of operation, we’ve had only a handful of spam accounts.

I was talking about this with Erin Kissane last year, as she and Darius Kazemi conducted research for their report on Fediverse governance. We shared a fear that Large Language Models (LLMs) would lower the cost of sophisticated, automated spam and harassment campaigns against small servers like ours in ways we simply couldn’t defend against.

23
24
 
 

The tech giant just signed a deal to buy fusion power. Meanwhile, company emissions are up 50% since 2019.

25
view more: next ›