Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude Code is steganographically marking requests

thereallo.dev

Post reply on HN
Print view View original

151–160 of 817 posts

Re: Claude Code is steganographically marking requests

#151

Post by chvid »

skeptic_ai wrote: post #118
meowface wrote: post #92

Value judgment aside: I am a bit surprised at how sloppily they did this. I think they could've achieved the same effect while decreasing the odds of detection via reverse engineering. (This field is known as "underhanded code", coined by the Underhanded C contest: https://www.underhanded-c.org . It's a little-known "art"; little-known for probably self-explanatory reasons. There are much cleverer ways of achieving o…

It’s even more funny how this blew in their faces. They even advertised pretty much all providers on hackernews home page. Here is in case you missed in the article ‘’’ cn baidu.com alibaba-inc.com alipay.com antgroup-inc.cn bytedance.net kuaishou.com xiaohongshu.com jd.com bilibili.co iflytek.com stepfun-inc.com moonshot.ai anyrouter.top claude-code-hub.app claude-opus.top openclaude.me proxyai.com yunwu.ai zenmux.a…

rhoooo - so this is where to go to get cheap Claudeo at 90% off the listing price!

Re: Claude Code is steganographically marking requests

#152

Post by pishpash »

mgraczyk wrote: post #127
realusername wrote: post #10

Earlier quoted context omitted.

They probably run a heavily dumbed down version of the model, same as what they got caught doing with Fable. And that's also why, as a legitimate customer, want none of it, you never know if you accidentally entered a zone they don't like.

"got caught" to clarify, this behavior was announced with the model release

The extent got caught.

Re: Claude Code is steganographically marking requests

#153

Post by crossroadsguy »

meowface wrote: post #92

Value judgment aside: I am a bit surprised at how sloppily they did this. I think they could've achieved the same effect while decreasing the odds of detection via reverse engineering. (This field is known as "underhanded code", coined by the Underhanded C contest: https://www.underhanded-c.org . It's a little-known "art"; little-known for probably self-explanatory reasons. There are much cleverer ways of achieving o…

I finally bought Claude Pro (I am not coding etc these days so I just wanted to try it). The Claude desktop app is downright pathetic. I mean they could write a better one just with their own LLMs. What's stopping them?

Re: Claude Code is steganographically marking requests

#154

Post by pishpash »

_alternator_ wrote: post #20
LPisGood wrote: post #3

This is very interesting. Combating resellers and distillation seems like a very difficult problem indeed. Interesting to me is that these techniques mentioned in the article are just like anti-observation techniques used by some of the more sophisticated malware out there, however defeating them is pretty trivial.

Yes, defeating this is relatively easy, particularly for sophisticated actors. But it's hard to always defeat all of the tricks. Sort of like how it's expensive and hard and uncertain to defeat all of the tricks when forging money. Here's an example. Say you have your team use patched binaries. Then CC updates and requires a new patched binary with new tricks. You now have to have a team ready to analyze the binary a…

Corporate surveillance malware on employee machines is also defeatable but most don't bother.

Re: Claude Code is steganographically marking requests

#155

Post by bel8 »

mgraczyk wrote: post #127
realusername wrote: post #10

Earlier quoted context omitted.

They probably run a heavily dumbed down version of the model, same as what they got caught doing with Fable. And that's also why, as a legitimate customer, want none of it, you never know if you accidentally entered a zone they don't like.

"got caught" to clarify, this behavior was announced with the model release

if by announce you mean shove it somewhere in a pdf with hundreds of pages, yes

Re: Claude Code is steganographically marking requests

#156

Post by epistasis »

After loving Claude Code for most of its lifetime, I've been extremely annoyed by every change in the past months, even on the model level.

There seem to be all sorts of continual under-the-cover changes like this one that make life harder. It feels like the entire product has been taken over by overly ambitious PMs that care more about making their mark than in improving the experience, and all of their marks have made me less productive.

I've been using Pi with GLM5.2 the past few days, and though it's expensive, I find it far more productive and less annoying. The remote session plugin is far more reliable, I don't need to intuit some undocumented usage pattern to figure out how to use it well, and it just works.

Re: Claude Code is steganographically marking requests

#157

Post by hn_throwaway_99 »

skeptic_ai wrote: post #118
meowface wrote: post #92

Value judgment aside: I am a bit surprised at how sloppily they did this. I think they could've achieved the same effect while decreasing the odds of detection via reverse engineering. (This field is known as "underhanded code", coined by the Underhanded C contest: https://www.underhanded-c.org . It's a little-known "art"; little-known for probably self-explanatory reasons. There are much cleverer ways of achieving o…

It’s even more funny how this blew in their faces. They even advertised pretty much all providers on hackernews home page. Here is in case you missed in the article ‘’’ cn baidu.com alibaba-inc.com alipay.com antgroup-inc.cn bytedance.net kuaishou.com xiaohongshu.com jd.com bilibili.co iflytek.com stepfun-inc.com moonshot.ai anyrouter.top claude-code-hub.app claude-opus.top openclaude.me proxyai.com yunwu.ai zenmux.a…

You have an odd definition of "blew up in their faces". What, do you somehow think your average Claude Code user on HN is going to think "Oh wow, I'm sure I'll get a much better experience if instead of going to the standard Anthropic Claude API endpoint I go through xiaohongshu.com."

Re: Claude Code is steganographically marking requests

#158

Post by AJ007 »

thih9 wrote: post #70
wolttam wrote: post #36

I used Claude Code for a month because my boss gifted me a sub and wanted me to try it. I used that month to complete a work project and then beef up my personal harness so I'd never have to deal with Anthropic (and these sorts of shenanigans) again.

How do people build something like a personal harness? Are there tools for that or is it done from scratch?

The real question is when do you transition from building it with codex/CC to the harness itself.

Re: Claude Code is steganographically marking requests

#159

Post by MichaelZuo »

slowmovintarget wrote: post #146
MichaelZuo wrote: post #93

Earlier quoted context omitted.

Does anyone know what’s gone wrong with Anthropic? They used to be a decently credible company with not-too-shady behaviour... I hope they can actually regain some credibility…

Their philosophy is what's gone wrong. It has some good effects on the their models, like Claude seeking cooperation first. But the people behind the company have a typical "unconstrained" (in the Sowell vision sense) perspective that assumes that they know better, so they are righteous for attempting to control things (users, paying customers, their model outputs, their tool chain, the supposed deity they assume the…

Yeah I guess there is a slight undertone that they are the superiors… with the rest of the tech world being the inferiors.

But I hadn’t thought that as anything more than temporary flights of fancy.

Re: Claude Code is steganographically marking requests

#160

Post by edude03 »

I don't understand the privacy concerns the author is trying to highlight. Granted, doing anything "sneaky" will always raise suspicious once caught, but on the other hand, there would be no point in implementing these "security features" if they were upfront about how they work.

And no, IMO stenography isn't security by obscurity, in the same that using RSA and keeping the private key private isn't security by obscurity - keeping the private thing private is part of the security model.

Post reply on HN