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

641–650 of 817 posts

Re: Claude Code is steganographically marking requests

#641

Post by YeGoblynQueenne »

solenoid0937 wrote: post #407
orbital-decay wrote: post #403

Earlier quoted context omitted.

>Please actually do a modicum of research into AI safety. Your comment is the equivalent of a patient with zero context, arguing against the position of established medical science. What makes you think I didn't? You're talking like it's self-evident and adopt the condescending tone from the start, without giving any actual arguments why. (I'm not really interested in them as all these discussions are pointless and w…

> Rationalists and subsequently AI safety branch invented a religion in a roundabout way If you are arguing in good faith you can very clearly reason about any given AI safety take. Case in point, you refused to engage with most of the questions because you know the conclusions they lead to. > Medicine is largely based on evidence and real-life observations, unlike AI safety "AI safety doesn't exist" is certainly a t…

>> Why do you think it's better that a country that turns its citizens into a pulp for criticizing the government, and censors most media to control its citizens' thoughts, reach SI before one that is democratically elected and in which you can generally criticize the government?

Stress on "generally".

Re: Claude Code is steganographically marking requests

#642

Post by jwrallie »

ed_elliott_asc wrote: post #591
jwrallie wrote: post #587

Earlier quoted context omitted.

You are not alone, for me committing something it means I am signing my responsibility for it. I may not type a password, but I am always the one pressing the enter key.

How do you stop Claude/opex from pushing or pulling without you asking?

I mostly program with Vscode/Copilot, where such commands require confirmation, but usually LLMs does not try it, since my prompts tend to be focused and not mentioning it.

Re: Claude Code is steganographically marking requests

#643

Post by tripzilch »

solenoid0937 wrote: post #496
silver_silver wrote: post #427

Earlier quoted context omitted.

> Do you know how their human rights violations compare to, say, western nations? You have to be joking

Please do some research on how they treat their own dissident citizens. 57k citizens disappeared since 2013, and another 5k every year. Their human rights lawyers sent to concentration camps, forced to eat their own shit, raped, and then murdered. Mere online criticism of the government gets you a visit from the police and gets you put on the watchlist. Often a few months' imprisonment without trial. This is not even…

You are out of your mind if you're lumping the US together with other western nations when it comes to human rights.

Re: Claude Code is steganographically marking requests

#644

Post by Laurel1234 »

solenoid0937 wrote: post #342
orbital-decay wrote: post #255

To summarize what they've already been doing: - filtering out people from the wrong side of "all humanity", years before it was demanded by the government - downgrading their models in arbitrary ways (later saying "sorry but not really") - actively sabotaging the replies, as in covertly modifying them to feed the users incorrect results What's next to expect from Anthropic? Malware to brick your machine if they don't…

HN hysteria is ridiculous. All of this is totally understandable if you take the perspective that these people genuinely believe they're building superintelligence. The overwhelming majority of the AI safety crowd - which has poured more of their life and time into thinking about these problems than the average HN armchair commentator ever would - understands that: - you want to prevent China from getting to superint…

> All of this is totally understandable if you take the perspective that these people genuinely believe they're building superintelligence.

They aren't, they are building LLMs. They aren't even building AGI and they all know it.

Hell, even if they came up with AGI, then Anthropic's service model would become slavery so I'm not sure why they'd want to.

Re: Claude Code is steganographically marking requests

#645

Post by skywhopper »

solenoid0937 wrote: post #389
Biganon wrote: post #387

Earlier quoted context omitted.

How does it lead to the end of humanity if China reaches it first? You really think the US is more trustworthy?

What are the PRC's values? How are individual freedoms in China? What happens if you criticize the government as a Chinese citizen? Is it a good thing if a government that turns its citizens into red pulp for criticism, or disappears them in the middle of the night, or bans access to most media, is the first to a godlike superintelligence that gives them de-facto control of (and impose their values upon) the whole wo…

Democratic nations, at the behest of their billionaire patrons, are rapidly pursuing China’s approach to governance.

Re: Claude Code is steganographically marking requests

#646

Post by tripzilch »

solenoid0937 wrote: post #497
rescbr wrote: post #431

Earlier quoted context omitted.

> Why do you think it's better that a country that turns its citizens into a pulp for criticizing the government, and censors most media to control its citizens' thoughts, reach SI before one that is democratically elected and in which you can generally criticize the government? Which country are you referring to? As an outsider who is neither American or Chinese, day by day it seems like the US is inching towards th…

You cannot be serious if you think this. Please do some actual research on how China treats dissident citizens. They ship their human rights lawyers off to concentration camps, force them to eat their own feces, then rape and/or murder them. 57k citizens disappeared since 2013, at least 5k more every year. I don't get disappeared for criticizing the US government online. The US government doesn't censor most media I…

> I don't get disappeared for licking the US government's taint.

ftfy

also maybe look up the history of the word "hysteria", that you seem to like so much

Re: Claude Code is steganographically marking requests

#647

Post by someonebaggy »

solenoid0937 wrote: post #410
orbital-decay wrote: post #409

Earlier quoted context omitted.

Can you substitute PRC/China for Anthropic and try answering your questions?

No company will own superintelligence. Governments will, just like governments own nuclear weapons (developed by companies). So the comparison is with the US, not Anthropic. The US doesn't turn its citizens into a fine red purée for criticizing it. The US doesn't censor most media. It is strictly better for a democratic nation like the US to get to superintelligence before a country that will gladly blend its citizen…

[dead]

Re: Claude Code is steganographically marking requests

#648

Post by Laurel1234 »

solenoid0937 wrote: post #381
Biganon wrote: post #379

Earlier quoted context omitted.

> HN hysteria is ridiculous. > this is a race that will result in the extinction of humanity if you fail in these goals

Ah yes, the very hysterical take that superintelligence must be carefully developed, or it likely ends badly for all of us. How irrational and hysterical of me!

Then why THE FUCK would we want to develop it? If you're so scared that what you're building will lead to our extinction, stop fucking building it. Why are you booster freaks so weird and psychotic?

Re: Claude Code is steganographically marking requests

#649

Post by avadodin »

Finbel wrote: post #498
pmarreck wrote: post #476

Earlier quoted context omitted.

[flagged]

Textbook fallacy fallacy.

Fallacy fallacy(and variants) implies there is a fallacy in the first place.

If the slope is slippery, it is not a fallacy to conclude that things will slide when placed on it.

Claiming something is a fallacy —when it is not— is simply a false statement of fact.

Re: Claude Code is steganographically marking requests

#650

Post by kuschku »

Considering this is tracking, processing, and transmitting data, and algorithmically making decisions about users, why doesn't this show up in their privacy policy, nor in their GDPR exports?

Sounds like a very expensive lawsuit waiting to happen (GDPR allows fining up to 4% of global revenue, not profits)

Post reply on HN