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

41–50 of 817 posts

Re: Claude Code is steganographically marking requests

#41

Post by ahmedehab_01 »

Frankly, I don't see this as the concerning behaviour the article describes. It is fine to try to protect against distillation through a technique like this. This will also allow them to, instead of blocking the distillation agents, respond with a poorer result/model, hindering the progress of distillation, momentarily at least.

I would guess that's their first line of defense; they should have more techniques to identify distillation because that's a very simple way of detecting the host and can be easily spoofed.

Re: Claude Code is steganographically marking requests

#43

Post by tonmoy »

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.

What models are you using? Aren’t you still dealing with some provider even if you are not using their binary

Re: Claude Code is steganographically marking requests

#45

Post by fny »

This was already discovered during the source map leak.

> This is not a malicious feature, but it is a weird choice for a developer tool that asks for trust.

They already tell you they scan for malicious prompts, and they have no ZDR guarantees for consumers. Why do signatures like this matter at all?

Re: Claude Code is steganographically marking requests

#46

Post by LPisGood »

dylan604 wrote: post #38
axutio wrote: post #30

Earlier quoted context omitted.

Would you also say that "someone who wants to use an IDE / LSP features to code and not give credit to the IDE / LSP is the worst kind of person"? If not, what is the difference between the two for you?

one wrote code while the other is used by meatbags to write code. why is this example always marched out like it means something?

Almost all ways of creating programs are effectively just using tools to produce code. Compiling, transpiling, interpreting byte code, etc.

Re: Claude Code is steganographically marking requests

#48

Post by palmotea »

axutio wrote: post #30
midtake wrote: post #13

[flagged]

Would you also say that "someone who wants to use an IDE / LSP features to code and not give credit to the IDE / LSP is the worst kind of person"? If not, what is the difference between the two for you?

> Would you also say that "someone who wants to use an IDE / LSP features to code and not give credit to the IDE / LSP is the worst kind of person"?

That's a false equivalency.

> If not, what is the difference between the two for you?

Let's start this out right: if they're equivalent, first you explain to us why you think so.

Re: Claude Code is steganographically marking requests

#50

Post by sebastiennight »

Can somebody clarify for me - if ANTHROPIC_BASE_URL is set to a different provider... then isn't this "marked" system prompt being sent to that provider's API rather than Anthropic's?

I understand how this can be useful to Anthropic if the 3rd-party is acting as a proxy (because they end up hitting the Claude API with the marked prompt), but it looks like requests where "hostname contains deepseek" would never be sending data to Anthropic. What am I missing?

Post reply on HN