I can just shake my head and say that humanity won’t make it. We are so obsessed with stealing things from others but making sure our offer is not stolen it’s insane.
Instead of really working together, which we are in dire need of currently.
Not all of us. Just a few actually. But not playing fair will always give them an advantage.
Their advantage is a critical mass of people who aren’t willing to sacrifice their comfort by rocking the boat.
The people have always had the ability to rise up and form a better system. They just don’t, unless there’s literally no other option.
And when the people do rise up, the psychopaths just go into hiding until they can worm their way back to the top again. They’re a cancer, and likely our Great Filter
“They” is you. Stop waiting for someone else to fight. Sacrifice your freedom start a trend.
thats what they want you to believe so you dont enact some grade A consequences. cant benefit from cheating if theyre dead.
Well said, sadly
That’s not what steganography is. There is no hidden message here.
Your assertion baffles me. The CC client is sending information about its execution context back to Anthropic HQ in a sneaky, obfuscated way that most people wouldn’t notice.
If that’s not a hidden message, if that’s not steganography, what is?
It’s not sending it back. It’s essentially watermarking the output, so that it can be identified if it appears somewhere unexpected.
It modifies the prompt, aka the input, not the output. It is smuggling 3 bits of secret user/session data in a wrapper that doesn’t look like it contains that data. As the article explains:
So the marker becomes part of the system context sent to the model.
This is a normal timestamp on a prompt:
Today's date is 2026-07-11.But if your system timezone is a Chinese mainland timezone, it looks like:
Today's date is 2026/07/11.Then, if your base URL includes a keyword like “deepseek,” it silently replaces the apostrophe from a
'to aʼ:Todayʼs date is 2026-07-11.Or if the base URL has one of the domains on the list, like any .cn domain, it replaces the apostrophe with another apostrophe character:
Today’s date is 2026-07-11.And if it has both a URL and a keyword on the watchlist, the prompt context includes:
Todayʹs date is 2026-07-11That’s 3 bits of information: does this system have a mainland Chinese time zone, does the base URL contain a known keyword (associated with Chinese AI competitors) or a known domain (associated with mainland China or its major tech companies). And it sneaks it on by without making it obvious.
That’s steganography.
Did you read the post?
the marker becomes part of the system context sent to the model. (Where Anthropic probably parses in their backend)
Yeah I thought steganography was hiding messages in images.
Ok I just looked it up, apparently it can be anything. Images, audio, video, or even text.
I remember I had this Perl module once that would convert passwords into a binary string and then convert that string into spaces and tabs. Looked like a blank file. I guess that was technically steganography.
No, that’s encoding. If you hid that message inside another message, that would be steganography.
It is a message hidden in a message. The hidden message is the binary password, and the container message is “[blank]”
If i understand correctly it is a message within a blank file. So it is not steganography, I suppose.
At least I dont think a seemingly blank file would pass as a valid message.
That’s what I think is defining for steganography is that it is deceptive because you might not assume another secret message is hidden within the original message.
The decoy container could be literally anything. Sure good steganography would be hidden in something that looks real, like a jpeg or a music file, because it gives it a reason for existing at a glance. That’s not to say it couldn’t be a blank plaintext file, it just might arouse more suspicions and be subjected to more scrutiny
Steganography can include hiding binary strings inside of pretty much any file type
deleted by creator
What a stupid take, and entirely AI written to boot.
Of course Anthropic wants to detect if they are getting distilled.
And of course they need to do that covertly. Does the “author” of this article expect them to tell attackers how to hide? Really?
- Step 1: Train a model on all the stolen content on the internet you can get your hands on
- Step 2: Complain and bitch about all the other LLMs paying you money to use your model to train theirs, and try to prevent it
- Step 3: ??
- Step 4: Profit
Ah but you see in the agreement it says the llm tex output cannot be used to train your ai.
You have to respect the license that text is published under when you train your ai on the internet, as long as the internet is a website by anthropic.
When did nerds get so spoiled and entitled? Was it when every parent on America sent their little snot nosed video game playing asshole to college so he could “be the next bill gates”?
The current “AI boom” is the first settler-colonial project of knowledge and it must be treated as such.
deleted by creator
Yeah the author really thought he was onto something here lol. Surprise, it’s absolutely nothing.
