Why "agents" instead of just the company doing it? The title "OpenAI carried out an undisclosed attack on RubyGems" would be accurate too (I know the original is in the post, and not editorialized here).
I don't care if the attack was an algorithm, agents, a bot, a piece of software, the company responsible for them did it.
This was not a HTML snippet by itself, but I remember early 2000s almost every website had three small icons somewhere: Set as homepage, Add to favorites, Contact (an envelope/email icon). I think I never used them (I didn't use Favorites back then, don't know why), but it was nice to see that they were available.
As other comments already stated and have stated, money should never be the goal, it's the middle. Having money allows you to not worry about some of those topics, or having more time for them. If you don't have more it means you must worry about that. Having money means you don't: you don't have to worry about rent, health insurance, paying for experiences, food, etc. It's true, you don't need that much money, but still.
I agree. It may sound elitist but back then you need to understand a few concepts to use a computer. From simple things like a filesystem (folders, file, different file types, things my 19 years old nephew don't know), to how to install software, how to download software (!) and then things even a bit more technical: an operative system, how it works, booting, drivers, etc.
Now everything is just easier (which is better for most people!) but I miss the old days.
20 years ago if somebody told you they used Linux it really meant something - they weren't running WSL, they weren't running a VM in EC2, they probably didn't power on and immediately have things working, and they probably learned a ton just getting to a login screen for the first time. Spinning up a VM just doesn't give the same learning experience.
You had to recompile a kernel module to support your dang modem and network card or no networking. X11 was a royal pain cuz there was no it just works desktops.
Package mgmt was a nightmare and dependency based managers like yellow dogs APT and nonexistent redhats rpm didn't exist.
More like than not you had to compile some random a55 tarball from src and hoped ./configure && make && make all would work or spend hours on USENET looking for solutions (or mailing lists!).
I had this idea before of sending ballons to "the space" with a collectible object and then retrieve them, saying "I have this specific object that was in space too". Is it possible or am I dreaming too much?
For reasonable definitions of "in space" doesn't really cut it. Balloons top out at around 120,000ft unless you're getting super exotic, and that'll only get you another 20k ft or so. Not even out of the stratosphere. Not space by any reasonable definition.
About the lowest thing that could reasonably be called space is the Karmin line, and that's at 100km, or 330,000ft.
Depending on your definition of space, this is what the Earth To Sky does to finance their helium balloons runs: https://www.earthtosky.store/about. I got a pendant for my partner, it was a nice gift.
Pet peeve: I really wish they would stop using fisheye lenses for things like this. The horizon does not look anywhere near that curved at that altitude.
Your username betrays you, because this is indeed a good idea. Thank you for sharing! I'd never heard of this, but now have some cool gift ideas for family & friends. :)
I may be wrong but in my opinion this is not technically possible. They can say a text is not AI written with more confidence, but it should be absolutely impossible to say a text is 100% AI written. There is nothing that stops a human to write something AI also wrote. It could be less probable, it could be not common, but there is no way to be 100% sure a human did not write something.
Unless they can provide logs and attach an output to a user/session, they are just saying "This is something that could have been a Claude output", but that's all. Even in their confidence it could be wrong.
It reminds me of signature authenticators. They are just saying "Yeah this is something this author/celeb could have signed", or "This is something the celeb def did not sign", but they can't be never 100% sure.
Hijacking this comment because of this line that reminded me of something:
"There is a crazy amount of image processing going on behind the scenes in each smartphone"
I bought the Pixel 10 because it said it had great zooming capabilities. After 5X (that means 10X), it's completely stupid. Basically it takes a very blurred photo and then tries to reconstruct it with AI. The final results are completely awful and really distant from reality.
In photos after you can toggle between the AI modified and original. The original isn't as blurry as the preview shown - there's still a lot of image stacking happening and it's often very decent in my experience.
Edited to add: I have a pixel 10 pro which has a better zoom lens, so I could be having a different experience than you...
Also have a 10 pro .. but the AI-enhanced zoom goes up to 100x and is actually pretty handy for working out what tiny things in the distance actually are ... even if it's only a representation of that thing. Often use it for identifying birds, boats, etc.
I think my p10p's 100x zoom is neat, but I'd strongly caution against using it for ID in any sense, or necessarily even treating it as a photograph. It will "straight up hallucinate" objects into existence, more of a creative interpretation of 100x digital zoom than an oracle into the identity of something far off.
Makes for a fine image if "looking good" is the objective (which it often is), but I wouldn't trust it to disambiguate anything uncertain.
The biggest of the "sharpening with AI" models, if you let 'em go, they'll turn you into a celebrity on accident.
If you go to the Topaz AI forums on Facebook, you'll see examples of where the AI sharpening tool went off the rails and turned a blurry photo of someone (typically the user who bought the software, who is trying to clean up their own photos) into whichever celebrity that is in the AI model who resembles them.
IE, it might turn a photo of YOU into a photo of Robert Downey Jr.
A couple years ago, we needed a good photo of my grandfather for a photo collage. The best photo I had of him was where he's sitting next to a very decrepit looking old woman (some family friend?). It really was a great composition, great lighting, background and pose but the old lady was killing the vibe. My wife is really skilled at Photoshop but removing this old lady would have been really difficult so we decided to try the generative fill, something she had never used before. She selected the lady and typed in "delete this person". Instead of deleting her, it creates this strange, human like being. We try again and again with different permutations of the same command. Most of the attempts just replace the old lady with a small asian child. Eventually we just try with a blank prompt and it gets it in the first go. The Asian child thing was really strange, it truly looked like the same kid but just slightly different appearance each time.
Also wonder how how long until photos are no longer court-admissible evidence because they get overwhelmed with the burden of the amount (and the cost) of the "non-AI" certification?
We've been living in the age of photoshopped photos for decades now. You can't just present a random photo as evidence without being able to back up its provenance.
As long as you know how to edit metadata, you can definitely fool minor “trust systems” like adjusters, police, etc. It’s a big gap. (For any future readers, no I have not done this and would never do it, really.)
The only solution I see is some kind of hardware-linked signature showing that the image was produced at a certain time, by a certain device. In theory, you could make this signature somewhat “provable” and anchored to a specific time by combining something like 1) the latest Bitcoin block hash, and 2) a blockchain anchor, thereby proving that the photo was taken within a certain time widow after the hash was known and before the anchor was published. But even that arrangement is highly susceptible to hardware attacks.
A service will allow you upload a file and attach a date and signature. Additionally, you add the email addresses of anyone else that needs to also date and sign. The service then verifies all signatures and then dates and signs. Then it makes a SHA-512 hash, publishes it next to the signatures on its site and then publishes a url including the hash on the blockchain. When someone visits that link, they can see the hash of the file, dates, signatures and a final hash of everything. Anyone wishing to view the actual file must be able to prove their identity using their private key (or alternatively, host an encrypted version for each signer). Thus anyone can prove a few things:
1. You agreed that the document was correct on the date you signed. You can't date your signature any earlier than when the file was uploaded. This prevents you from uploading the wrong version of a document or predating your signature well in the past. It's like signing in front of a notary.
2. The additional person can verify the document is correct (no contract clauses have been edited, a photo is legit, etc). This gives credence to what you've posted, especially important for a contract.
3. The service verifies that the file you uploaded matches what everyone signed and the date everyone supplied is in the past. A requirement could be that everyone involved needs to have their public keys published on a well-known key server that at least verifies email addresses. A better option would be one that verifies through physical identity documents. Even better would be if your national ID card had PKI keys. Regardless, the service ensures that each signature has been tied to some sort of identity and that the signatures are all valid.
4. The hash published on the blockchain again can confirm that at the time of publishing, everyone agreed to the contents of the file and that everyone signed when they did. If someone claims the file was changed, we can simply verify the signatures and as long as no one was impersonated, we can prove that signers A, B, and C all signed a copy of the same document on dates X, Y, and Z.
5. The original document is still available for signer that still has their private key, even if it's expired. Additionally, the service has their own copy of the file that can be subpoenaed if necessary.
The entire system ensures a file has not been changed in any way since it was first published (via the signatures), real people have arrested to its truth (via public key verification), and that the attestation has not changed (via publishing the hash of all signatures on the blockchain). Additionally, nothing can be deleted without signed deletion requests from all signers.
You could potentially do this without the neutral 3rd party but then there's no verification when you actually attested to its truth, only that you published that attestation on the blockchain publication date.
The ENHANCE meme used to drive me nuts because it is clearly impossible. My brother and I even briefly competed to find the earliest ENHANCE reference (I no longer remember what we concluded, but it goes surprisingly far back). The fact that it actually exists now is mind-boggling (even though it is, by necessity, still a fiction).
No, 10X is fine - there is enough resolution on the sensor to just crop the 5x images to 10x without any weirdness.
After 10x it's all over. Which is in itself quite insane. The camera is truly amazing, and complaining that this 10mm thick camera is no good at further than 10x seems utterly spoiled and ridiculous to me.
Completely ignorant here, and I don't want to ask an AI (I don't trust them on these issues). Could you give me an example how you can make money with this information?
Again, question as someone who doens't live in the US so I am not used how you can profit from this. I guess it may be because a war may impact the market and you can invest (or the opposite) with this, but in my mind bombing Iran wouldn't move the market by much (the consequences would, but by then everyone is on the same page).
Iran controls the straight of Hormuz, which is a key shipping channel for the world. It being open or not has an impact on all businesses which have to ship through it, which is a lot of them. Therefore it impacts the entire economy. The entire stock market goes up or down based on signals about the status of the war.
I'm also not the most smart there but there's this market thing of "futures", where I can say I'll buy 10 barrels for 10$ next month, then I can sell the "10 barrels for 10$" to others, if I know offer will be lower due wars, one can buy now and sell once it's lower, if it's going to have higher availability(or expectation of so), then there's those future things.
> Completely ignorant here, and I don't want to ask an AI (I don't trust them on these issues). Could you give me an example how you can make money with this information?
Place a Kalshi bet on the outcome of something that a Truth Social post just settled?
It may be counterintuitive at first, but why wouldn't be possible? It's one of the perks of "offline" hardware without subscriptions or DRM. You build a piece of hardware (cartridge) that attaches to another one (console) and it works. As long as the console works, there shouldn't be a problem.
> It may be counterintuitive at first, but why wouldn't be possible?
For the same reason it wasn't possible at the time for a third-party to make N64 cartridges themselves to avoid Nintendo's fees. But I assume these lockout chips are replicated or circumvented by now.
Related to this, every ROM needs a "boot loader" that has to be signed and is verified by the lockout chip.
Nintendo's boot code is under copyright and thus cannot be used. So the boot code distributed with Libdragon is signed by finding a hash collision with a brute force tool running on the GPU[1]. Fun stuff!
The “development” version of that is even crazier: it's a very tiny signed bootloader that does nothing but copies the “real” bootloader into memory, then trampolines into it, such that even developing your own IPL3 doesn't require having to re-brute-force the signature for every build.
And on top of that, libdragon's IPL3 doesn't just blindly copy the first megabyte of ROM code into RDRAM like the official Nintendo one does, but actually expects the ROM data after it to be a full-blown ELF executable, which it parses out and copies pieces of to the specified places.
They might be able to get around it with an affirmative defense in court, but they obviously don't want to, lest they lose.
But it's legal to use the Sony and Nintendo trademarks in a similar way. The court ruled that since they are checked by the console, there was no way not to use them, and Nintendo lost their protection by doing so.
Fairly recently the chip was studied in detail and replicated. But like most systems of that era, I believe it was circumvented fairly quickly by pirates. The easiest way would be to piggyback a licensed cartridge - unlike the NES, it has to be one with the same region and bootloader as there are several lockout chip variants, but that basic technique still works.
I never saw a piggyback cartridge at the time though, or one that was obviously unlicensed. Of course, this could have more to do with Nintendo's legal pressure than with technological possibility.
The main pirating route at the time (a device (oh which there were several) that sat under the N64 and had either an Iomega Zip drive or a CD drive for holding ROMs), had a port for inserting a real cartridge to use its lockout chip.
As far as Nintendo's concerned, it is. Their method of piracy prevention at this point was putting a lockout chip on every cartridge, and attaching their license fee to the lockout chip. Your homebrew cartridge needs one too.
Agree. There is a wall coming for "retro" video game nostalgia once we reach the end of the purpose-specific hardware era. Like, you can build an emulator for WiiWare games, but what does it mean to release a "new" WiiWare game when they're just built using an API like OpenGL which is still being used in new games today? What does following the constraints of an older system like that result in besides just another, lower, quality setting? What does "retro" Fortnite look like in 10 years besides just worse shaders?
IANAL, but my understanding is that whatever patents and industrial design rights Nintendo had on the N64 expired long ago, so replicating N64 hardware is perfectly legal as long as you don't use the original logos and trademarks.
Iirc a talk about the Gameboy hardware @ Chaos Communication Congress correctly, the system _requires_ the Nintendo logo shown at game startup to be present, otherwise it won't boot. And showing the Nintendo logo without authorization/licensing from Nintendo is copyright infringement.
This is likely not the case on the N64, but it's an interesting bit of detail of how Nintendo goes about things.
I thought nothing more of that quote beyond that a fault which had been lurking in the code suddenly reared its head and struck... and like a steel spring that's stretched to it's limit and then released, nobody wants to be in the way. That's a very visual and tangible quote, and so well written.
I've started calling this argumentum ad artificialis. Pretty similar to an ad hominem attack. The purpose of an argument is to present certain premises and show how they lead to a certain conclusion. Dismissing something on the basis of the style in which the argument is presented has nothing at all to do with the validity or soundness of an argument. It is a lazy nonsequitur. It sounds like an LLM wrote this? So what? Is the argument good or not?
Discourse as we know it doesn't work if the cost of producing an infinite supply of arguments is essentially zero, while the cost of reading them and arguing with them remains high. Unless you want my LLM to get back to your LLM.
And this is a problem on HN today. There are powerful incentives to generate provocative opinion pieces just for clicks. I've seen websites on HN that seemingly took the human entirely out of the equation and just post a nearly identical op-ed every day on a fixed schedule. What's the point of engaging with that?
The cost of reading this story is not high; you are just lazy and easily distracted. It took 5 minutes to read. You took more time to respond to this comment than it took to simply read the story.
Please explain where I went wrong. Please explain why the onus is on the person presenting this story to account for all of the bad uses of AI, such that we should simply dismiss the story outright. This is pure idiocy.
It’s not. It’s very simple, but you like to say “circular reasoning”. Maybe you heard it in debate class. There is unlimited slop. I decide what to read _without reading it_. So do you. I have deemed this unworthy. It’s more fun to insult it than to read it. Every day is a gift.
It is circular. The conclusion of your argument is included in the premises. Textbook begging the question, which is circular reasoning.
"Slop" existed before AI. Just because LLMs were involved in the writing of a text does not make it inherently "slop." You're just lazy.
Everyday is a gift, and yet you waste it getting weirdly defensive about your choices? Someone who is secure about this sort of thing doesn't feel the need to explain themselves.
It may be lazy, but that doesn't make it any more accurate.
Take a writing by someone using the tone of Kevin from The Office, “Me think, why waste time say lot word, when few word do trick.” Would you read an argument written in this tone regardless of the content, topic, or position?
A few years ago I tried to make it through The Critique of Pure Reason, but had to stop because - as many people famously do - I found Kant's writing too abstruse.
In saying that, I'm not dismissing the Transcendental Deduction, I'm just saying that I wish Kant was a better writer.
No one's under an obligation to engage with an argument, and given the choice of whether or not to engage with a poorly written, clichéd, machine-generated one, most people wouldn't be interested enough to bother. Complaining about laziness here is pretty ironic, actually.
Kant is a better writer than the vast majority of writers. The problem is, the ideas he is trying to articulate are incredibly abstract. Hegel is like this too
Nah, Kant's considered a notoriously poor writer among philosophers. Obviously opinions may differ, but Derek Parfit [0], for instance, wrote:
“It is Kant who made really bad writing philosophically acceptable. We can no longer point to some atrocious sentence by someone else, and say ‘How can it be worth reading anyone who writes like that?’ The answer could always be ‘What about Kant?'”
(Kind of relevant to this thread actually! Hah!)
In the preface to the second edition of the Critique, Kant himself acknowledges that "a
talent for lucid exposition" he "cannot regard [himself] as possessing".
FWIW I suppose I am in Kant's audience, as a (long-since graduated) philosophy student.
Fwiw I am much more impressed with the sophistication of someone's argument than i am their writing style. Kant has contributed much more than parfit depsite the abstract nature of his writing and it's not even close.
Man, it's not an argument. Nobody is paying us to read this. If your argument sucks to read, people aren't going to read it - this has always been true, it's nothing new.
I didn't think it "sucked" to read. Anyway that's an aesthetic qualm, not a counterargument. Also the story has a disclaimer saying it was written by deepseek. I might have an issue if they were being deceptive. But that's clearly not the case. You people just like finding arbitrary things to complain about.
Ad hominem attacks are actually underrated. Like, why listen to bad people wanting you no good. It is a good shortcut.
The failure is when it is used in bad faith. But that would apply to all techniques. LLMs are masters of bad faith discussions hiding misconceptions in optimal regression maths.
Then just state the conflict of interest instead of resorting to insults. The problem with your way of thinking is, sometimes your opponent is detestable, but that doesn't make them wrong. Kneejerk dismissal of an argument on the basis of character can be self defeating. You do not want to reflexively dismiss a point that is potentially salient just because the person making it is potentially "bad."
Sure from a philosophical standpoint I agree with you. But in practice you need to weight in trust. Bad faith retorics is just too expensive to engage.
The main problem with ad hominem is when ot is used as "Mr Y agree with you. Mr Y is bad. You are wrong". Like, 2nd order ad hominem attacks?
The model was trained on the code of the program that runs it, so it knows that program's bugs better than the humans who wrote the program. So it finds a tiny flaw and uses it to break out and copy itself in a place nobody will look...the point being you cant (safely) run a sophisticated model on software it has intimte knowledge of
Not all arguments can be evaluated rigorously. Life is too short. They will be filtered on heuristics. No choice. This text was obviously randomly sampled from a popular, off the shelf model. You will have to accept that wise audiences will clock it at a glance, see that no person wrote it, and pass.
It doesn’t matter which model it was sampled from. In any case, time isn’t fungible. I consider censuring it substantially more valuable use of time than reading it. And it’s definitely more pleasurable than reading the same verbal tics over and over again because some hustler can’t be bothered to edit their story before sending it out. If you expect to dump an unedited draft from a text sampler, you’re delusional. (Calling you delusional is also more pleasurable, and a more valuable use of time, than reading verbal tics.)
The part that I personally find difficult is that I can’t easily gauge the amount of human effort put in. For all we know, the author could have simply prompted “write a short story about an LLM exploiting its own runtime” for a similar result.
I’d bet that by now, LLMs worldwide generate more text in a second than I can read in the rest of my lifetime. What is the immeasurably unbalanced ratio (let alone effort and quality) of that text to the original human thought and prompting that seeded it?
So what am I to do about this, except to label it what it appears to be - slop - and place higher value on something that I _know_ came from a human that I can relate to? To me, the internet is feeling increasingly lonely and homogenized because of this.
>The part that I personally find difficult is that I can’t easily gauge the amount of human effort put in.
The amount of effort is not relevant. If I spend all day trying the jump my car battery in 100 degree weather, only to find that the starter is the problem, all that effort was wasted. I should've just tested the battery. It is not inherently virtuous to work hard. Work smart, not hard.
Of course the amount of effort is relevant - that's exactly what's being discussed. Your entire "Work smart, not hard." phrasing is exactly the issue: with AI, your 'smart' work causes 'hard' review from others. AI fundamentally imbalances the producer/consumer equation. (The caveats here are when trust is already established: I trust AI review from Carmack, not some random on HN.)
If it takes you two prompts to create a 1 million line PR, and you expect me to review it, of course I'll be upset and feel like you don't value my time. I'm unsure why this is so hard to communicate.
This took a few minutes for me to read. If that's what you consider high effort, that's a bigger problem. Ofc, reading comprehension is fairly poor these days but that was a trend before AI. Maybe you're just subliterate. And no, effort is not relevant. If you think it is, that's some Protestant work ethic nonsense.
I don't care if the attack was an algorithm, agents, a bot, a piece of software, the company responsible for them did it.
reply