Claude Code Is Steganographically Marking Requests
https://thereallo.dev/blog/claude-code-prompt-steganographyOpen linkView original on reddthat.comSyndicated from the fediverse. Read and engage on the original instance.
View original on reddthat.comhttps://thereallo.dev/blog/claude-code-prompt-steganographyOpen linkView original on reddthat.com
40 replies
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
Is this comment AI or just regular run of the mill Lemmy doomerism?
ahh just the regular AI shilling comment from eyekaytee. do you comment in any other topic whatsoever?
🤔 just look at my profile?
It’s always funny to see comments like this, dismissing AI critics by calling them “doomers”, while society as a whole is still dealing with the consequences of the last widespread tech fad: social networks.
social networks are over 20 years old, think you need to look up the term fad :p
Sorry about that. Let’s call it “another technology specifically designed by large corporations to be extractive and destructive”.
well I mean AI helps me every day at my job, there are jobs I would have turned down before that would have taken thousands of hours but thanks to AI I only spent 10's of hours on them
I also use AI 5-10 times per day for personal reasons
Social media on the other hand is a plague of garbage and I wish facebook and twitter would be deleted off the net
Weird take. You would have turned down a job because it takes “too long”? The whole point of wages is to get money for your time.
Also, highly doubt something that would take you a “thousand hours” now can be done with AI in tens. Something useful, I mean.
You clearly weren’t around when it all started. Social media was peddled as a legitimately useful thing. People organized around Facebook groups, and stopped paying telecommunication companies for SMS usage because of WhatsApp. LinkedIn became the dominant player in white collar job seeking. In Asia, super apps like Line or Kakao or WeChat became so popular, they became the mainstream way of finding, contacting and paying businesses for services. Twitter was the place for legitimate reporters to post short form content.
It all went downhill afterwards. Most people thought, at the beginning, that social media would revolutionize the world as we knew it. They just didn’t know it wouldn’t be in a good way.
Maybe put your response into AI and have it re-write it for you to come across as less of a dick
I think the latter
A brief glance at the entire history of humanity would indicate that what they are saying is true.
Less than 0.01% of human history has even been documented...
Just because you can't imagine anything better than what you were raised in doesn't mean it can't exist...
This too shall pass.
In case you're really interested I am alive and well and able to think myself. It's neither and if you don't agree that's absolutely fine by me.
It's one of the things I'd live to be proven wrong.
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:
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?
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
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?
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.
Yeah the author really thought he was onto something here lol. Surprise, it’s absolutely nothing.