I want the right to not be identified.
I also want the right to SELF identify.
I think the toxic culture of the internet has happened in part because anonymity leads to lack of accountability. I want to self identify and interact with other people who also self identify. The cost of running LLM botnets is going down. I cannot imagine how the next cycle of elections is going to be like on all countries. I understand the right to remain anonymous, that should remain, but that state should not be the default on these massively big platforms. Our brains and political systems are not designed for this.
And no, "get people to get rid of their smartphone voluntarily" like I see on the comments is not going to happen.
> I think the toxic culture of the internet has happened in part because anonymity leads to lack of accountability.
It is trivial to demonstrate that this is incorrect (despite sounding plausible). There's plenty of incredibly toxic behavior to be found all over facebook.
Among other considerations it's worth noting that most of the usual social feedback mechanisms are missing from typical online interactions.
> The cost of running LLM botnets is going down.
Agreed that this is an existential threat to anonymous discourse as it is typically implemented.
There is vastly more toxic behaviour on Facebook, it's not even close.
If there's a severity to toxicity then perhaps 4chan can peak at a 9/10 whereas Facebook posts peak at a 7/10, but there's orders of magnitude more people posting on Facebook. If you pull in Facebook comment sections on news sites and consider those too, these threads where people publicly call for torture, rape and death, you realise that 4chan has an unearned bad reputation compared to the mainstream.
I'd wager the amount on FB is orders of magnitude _more_ than on 4chan. 4chan's average severity is likely higher, though. They're different problems, but saying that online toxicity only exists on anonymous sites is naive at best.
They didn't say that, they said "anonymity leads to lack of accountability". Even the counter that authenticated sites have users engaging in toxic behavior doesn't contradict the original point.
The clear implication of the earlier statement in context is that lack of anonymity should be expected to reduce the practical aspects of the problem to a useful degree. I believe the general state of facebook stands as a stark counterexample.
That said, I do think it's a fruitful line of inquiry to wonder why that might be the case. Are there any known cases where anonymity alone is sufficient to tip the balance towards widespread toxic behavior? Related to that, if lack of anonymity frequently does not curtail toxicity then what might the important differences be versus real life interactions that can account for it?
Yes, it is far worse because it gets personal far more quickly with non-anonymous users. People don't feel exhausted by 4chan, it is mostly the comparison to others on "legit" platforms.
And to be frank, there is value in 4chan. Nobody would feel compelled to believe obvious bullshit some societies and cultures impose on its members. This shit needs a counterweight. That isn't 4chan of course, but any free platform.
In fully anonymous platforms like 4chan it also just takes one participan to step away to end a dispute unlike non-anonymous or pseudonomynous platforms where there are more avenues for continued harassment.
But really to have this discussion we first need a better definition of what we are talking about than nebolous "toxic behavior". I don't think anyone is going to dispute that 4chan posts are more likely to use crass language than those on Facebook so perhaps that is what gp considers toxic.
Exactly and the typical societal feedback mechanism for bad behavior are more terrible than the original problem when they are expanded to internet scale and become cancel culture.
Yep, and the alternative is simply ignoring the bad behavior and forgetting about it only minutes later.
I've walked away from so many online conversations by simply not replying, and everything's fine. Those are now just dangling threads in the void that almost no one will discover or care about.
Toxic culture was always there but it really took of with social media where users often have zero shame to self-identify. There are anonymous communities that are far more friendly than the common insta group. "My brain" is perfectly fine with anonymous users.
And yes, anonymity should be the default because otherwise the alternative is that you need to identify. If not, most users would stay anonymous because it is simply the smarter decision with the exception that you seek exposure.
The only reason I'm public and use my real name in some social media contexts is for career exposure, so I can discuss my profession with others in hopes that it interests someone enough to offer me a job or build connections for later.
Outside of that, I have no reason not to be anonymous, and unfortunately it's too risky after the kinds of cancellation campaigns we saw during COVID over procedures, and around the same time, the all-or-nothing nonsense around whether you supported the BLM leaders' mansion fund.
It's not worth losing a job over seeing the writing on the wall before everyone else does, and calling it out publicly.
>I want to self identify and interact with other people who also self identify.
You can do that already, Facebook is pretty close to exactly what you're talking about. They do a lot of work to identify real people and de-prioritize spam/bots. You can configure your account to only be able to interact with real people if you want. Many people like anonymity though, it's important for speaking truth to power and discussing topics which are outside the Overton window.
There's a good reason that many of the United States' founding fathers used pseudonyms when writing. Anonymity and real freedom of speech are foundational to democracy. If you can put someone in jail for saying something that the government doesn't like, then the government will be able to steer discourse towards outcomes it deems acceptable, even if those outcomes subvert the will of the people.
There's no real need to have the government force all websites to always authenticate all humans. The only real argument for such a system is to move us toward dystopian authoritarianism.
We need LLM query routing at the OS level like Mobile data.
I know it will sound crazy but hear me out. I think about this AI inference as infrastructure. I do not want to pay for it on every app I use it on. I do not think "I have to pay the mobile data of youtube, and the mobile data of whatsapp etc.". I pay Mobile data infrastructure and let my device route it appropiately. In fact, if we ever go the local llm route, you could have LLM capabilities without having access to the internet (or local LAN), and your OS/computer is the only one capable of doing that routing for you.
It doesn't sound crazy at all, this seems almost obvious. The OS should provide a chat completions server and the user should be able to select the underlying LLM's server. This should be just like selecting a default search engine or browser.
Hopefully the EU forces US tech giants to do this. God knows Apple and Google won't do this on their own. They gotta get that sweet default provider revenue.
> It doesn't sound crazy at all, this seems almost obvious. The OS should provide a chat completions server and the user should be able to select the underlying LLM's server. This should be just like selecting a default search engine or browser.
I wonder why this hasn’t happened yet. If Microsoft wants to have a Copilot button and AI investments are all the rage now, surely anything to make integrating with them would be good for keeping the hype cycle alive for longer?
Apple told EU Citizens thats why they cant have Siri on their Phone as AI; they would have to provide an Interface where you can plug in your own LLM of your chosing.
Honestly I don't get the point but if you want to explore that, both on desktop, mobile or headless server Linux allows you to try it.
You can run ollama with whatever you want on a Debian in literally minutes. You can even do that within a virtual machine using e.g. QEMU, so that you can do all the tests you need risk free.
Again I don't understand what that would enable that can't be done today but it's perfectly fine, you can try today anyway, no need to ask permission to anyone.
I am saying I want my OS to expose APIs like it does for the disk or the network for AI. And I want my apps to be able to use those APIs.
I want my backend LLMs to be able to change on a whim.
Imagine an Android app consuming from these LLMs. Maybe I am outside and it is making queries to Gemini. And maybe I get home and now it makes queries to my local llm, almost like connecting to local Wifi.
What I am saying does not exist on many levels:
- Agreed upon APIs for this don't think exist (in text maybe, but not in image/sound/video).
- OSs do not expose this (I am not talking manually configured user space stuff here).
- I see a world where your Network provider bundles "calls + data plan + AI tokens". But not only are the offerings for these not standardized, in order to even reach that point we would need to standardize the offerings. How do you compare intelligence among models? How do you compare cost?
Well… it doesn’t exist FROM APPLE or MICROSOFT or GOOGLE at their shipped OS Level, but… fundamentally this isn’t a “true OS” level feature you’re asking for, it’s something you think the OS products should bake in, and you might be right! But I think the parents post is suggesting YOU CAN BUILD a prototype of what you want, how it should work, on Linux…
I have a project somewhat close to this I’ve put on pause the last month or so, partly because I’m not sure how useful it is or where to take next, but I may incorporate Wayfinder into it as a next step to improve its capabilities, as part of what it is a model gateway/router that this feels like could make more powerful/flexible in its decision making. I can’t decide if what I’m building is mostly a model recipe cookbook/platform, or a debugging tool, or both or something else at the moment, but, it can do most of that… maybe it’s part of what you want, if you figure that out better? feedback welcome!
https://wardwright.dev/https://github.com/bglusman/wardwright
> Well… it doesn’t exist FROM APPLE or MICROSOFT or GOOGLE at their shipped OS
What I am saying does not exist period. What I am saying is that there isn't a proper abstraction that helps the ecosystem build upon it.
> But I think the parents post is suggesting YOU CAN BUILD a prototype of what you want, how it should work, on Linux
I mean, yes. But me saying "this does not exist" and someone saying "but you can build it" does not take away from the fact that... Yeah, it doesn't exit :).
And also, no, I cannot build it, at least not alone. Because I want apps to eventually build upon my abstractions. This would require a good set of millions, of which the technical development would be a small part. The coordination, contracts, API definitions, even marketing, etc would be the majority.
I am saying something that Google, Telefonica, Microsoft etc could do.
Exactly. That's why I built the role-model protocol, the pi-role-model extension so that Pi can tell the router where its requests should go, and the reference router implementation: https://news.ycombinator.com/item?id=48706181
I mean, the reason mobile data is part of the OS is because the antenna is hardware that must be shared across processes. Chat completions is just a network call like anything else—it’s already available to every app; they don’t need to pay separately (they can use the same account), they just pass their API key over the network to the completions server. What am I missing?
> Chat completions is just a network call like anything else
But what if Chat completion was resolved locally with hardware? Or what if I want my OS to coordinate Chat completions locally and, if my hardware is overwhelmed, send some to network?
You do have a valid point, yes, that what I am saying, without support for local hardware could be done with a sort of Open Router equivalent.
> they don’t need to pay separately (they can use the same account), they just pass their API key over the network to the completions server
That I would be conformable putting what I am saying on my parents phone. I do no trust my parents to manage API keys. What I am saying is an ecosystem thing, not only a low level thing
I want to add that Obscurity is ambiguous.
Is changing the port of SSH "obscurity"?
Some may say yes, because you could find it by bruteforce.
But a password with infinite attempts can also be bruteforced.
Here, the defining factor of security is maximum number of attempts (either on ports, username or whatever).
I haven't had time to see the whole thing yet, but I'm quite surprised this yielded good results. If this works I would have expected CPU implementations to do some optimization around this by default given the memory latency bottleneck of the last 1.5 decades. What am I missing here?
Not only would be cool for laws to have appropiate time stamps so we can "go back in time to how it was at a certain moment", but also if we could have proper git commit diffs of how laws change over time. See this: https://www.boe.es/buscar/act.php?id=BOE-A-2015-11430
You can see how certain articles have the option to check "how that particular article was at each moment in time". That would be way harder to track, but it would be awesome if not only could you "go back in time and see what the law was" but also "how its been evolving".
Then compare wording and structure with other bills proposed elsewhere to look for single sources trying to legalize an agenda or retry after earlier failed attempts.
People use their phone today to: Manage 100k+,1M+ bank accounts, 2FA, secret messaging, sensitive media, medication, credentials and more.
This privacy feature makes a lot of sense.
Give it a couple of iterations and I think this will be the standard in business. It never made sense to me the trust that we put on no one looking at the contents of a display at the same time as us.
I'm much less concerned about a rando looking over my shoulder than I am the wealth of information the software hands out to its owners. It's like the difference between being seen in public by other pedestrians versus being captured by thousands of fixed surveillance cameras. Look all you want, so long as you're not wired into a database. Different threat models, I guess.
The people who are genuinely concerned about shoulder surfing probably slapped on a privacy filter anyway. They're no different from a screen protector. What the S26 Ultra can do is cool and super useful for the few people who need it, but I'd bet that all the rest will just show it off as a cool party trick and nothing more.
I've seen this with laptops that came with integrated electronically controlled privacy filter. They were nice but eventually the added cost, complexity, and lowered image quality didn't make them a popular choice even for enterprise users. I think only HP still offers them from the big brands, Dell and Lenovo don't do it anymore.
> The people who are genuinely concerned about shoulder surfing probably slapped on a privacy filter anyway.
So only the people concerned about it should get privacy?
> They're no different from a screen protector.
Privacy filters are way worse than screen protectors, they permanently degrade your display experience by a LOT, and you cant turn them off when you dont need them.
> I've seen this with laptops that came with integrated electronically controlled privacy filter.
Which are a completely different thing than this privacy display.
> lowered image quality
Exactly, these addon filters or layers degrade image quality, this new display doesnt. In normal mode its just a normal 2600 nits, HDR, 120hz, and whatnot OLED smartphone display.
> So only the people concerned about it should get privacy?
To call this an uncharitable interpretation would be an understatement. The phone has a feature that costs money and if you look around you’ll see most people don’t bother with this concern.
It has nothing to do with “should”. I have the same privacy now and for way less than the price of that phone. The solution for privacy exists already and the one Samsung offers was already “rejected” in the past because of the added cost most likely. Why do you think it comes on one of the most expensive phones on the market?
> these addon filters or layers degrade image quality
You didn’t read my comment carefully. I wrote specifically about integrated electronically controlled privacy filters on screen laptops which lowered image quality.
A phone at this price level already targets a tiny niche just because of affordability. A small part of that niche buys the phone because they want the privacy screen.
Or displaying your card out in the open, flashing it in front of everyone in the restaurant, grocery store, etc. With remote workers scanning through video feeds of people in public, it won't be long before they figure out the Meta glasses and similar cameras are high enough resolution to capture sensitive information, even if the actual user is 100% innocent and not doing anything wrong.
There was a gas station cashier that was using a memory palace trick to memorize card numbers and details, then stealing money later on. The bar was one of a little effort - not many people can do the memory palace thing, so it wasn't a threat vector. Now, everything is being recorded all the time, and you basically have to trust that everyone in the long list of people who have access to the video won't use it maliciously. We absolutely don't live in the type of society where that type of trust is warranted - there's gonna be lots of crime from unexpected places.
Throw in capturing logins, secure pins, touchscreen swipe sequences, etc, it won't even matter if you have all the best security features in the world.
Maybe implanted cryptographic key devices are the way to go, and you have to go into a perfectly secure SCIF with a faraday shielded closet in order to enter in your personal key, which can be used to provide tokens for other logins, verify actions, etc.
While this is great, I expected faster CPython to eventually culminate into what YJIT for Ruby is. I'm not sure the current approaches they are trying will get the ecosystem there.
I implemented most of the tracing JIT frontend in Python 3.15, with help from Mark to clean up and fix my code. I also coordinated some of the community JIT optimizer effort in Python 3.15 (note: NOT the code generator/DSL/infra, that's Mark, Diego, Brandt and Savannah). So I think I'm able to answer this.
I can't speak for everyone on the team, but I did try the lazy basic block versioning in YJIT in a fork of CPython. The main problem is that the copy-and-patch backend we currently have in CPython is not too amenable to self-modifying machine code. This makes inter-block jumps/fallthroughs very inefficient. It can be done, it's just a little strange. Also for security reasons, we tried not to have self-modifying code in the original JIT and we're hoping to stick to that. Everything has their tradeoffs---design is hard! It's not too difficult to go from tracing to lazy basic blocks. Conceptually they're somewhat similar, as the original paper points out. The main thing we lack is the compact per-block type information that something like YJIT/Higgs has.
I guess while I'm here I might as well make the distinction:
- Tracing is the JIT frontend (region selection).
- Copy and Patch is the JIT backend (code generation).
We currently use both. PyPy uses meta-tracing. It traces the runtime itself rather than the user's code in CPython's tracing case. I did take a look at PyPy's code, and a lot of ideas in the improved JIT are actually imported from PyPy directly. So I have to thank them for their great ideas. I also talk to some of the PyPy devs.
Ending off: the team is extremely lean right now. Only 2 people were generously employed by ARM to work on this full time (thanks a lot to ARM too!). The rest of us are mostly volunteers, or have some bosses that like open source contributions and allow some free time. As for me, I'm unemployed at the moment and this is basically my passion project. I'm just happy the JIT is finally working now after spending 2-3 years of my life on it :). If you go to Savannah's website [1], the JIT is around 100% faster for toy programs like Richards, and even for big programs like tomli parsing, it's 28% faster on macOS AArch64. The JIT is very much a community effort right now.
PS: If you want to see how the work has progressed, click "all time" in that website, it's pretty cool to see (lower is faster). I have a blog explaining how we made the JIT faster here https://fidget-spinner.github.io/posts/faster-jit-plan.html.
Thank you for your contributions to the Python ecosystem. It definitely is inspiring to see Python, the language to which I owe my career and interest in tech, grow into a performant language year by year. This would not have been possible without individuals like you.
I think the direction we are going, the GPL is going to fade away. I think people will look at this like writing a book and claiming the ideas in the book cannot be copied. This debate is not that different from the ones going on in the music industry. I open sourced my latest software as Apache 2.0 after debating a lot about this. Unless the FSF wins in court in the next <=2-3 years, there is no coming back from this.
Reminder that OpenAI serves a lot of customers for free, most of the people I know use the free tier. There is a big limit on thinking queries on free tier, so a decent non thinking model is probably a positive ROI for them.
> computer science students should be familiar with the standard f(x)=O(g(x)) notation
I have always thought that expressing it like that instead of f(x) ∈ O(g(x)) is very confusing. I understand the desire to apply arithmetic notation of summation to represent the factors, but "concluding" this notation with equality, when it's not an equality... Is grounds for confusion.
