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

Stealing Reasoning Traces from Proprietary LLM APIs

stolen-thoughts.com

Post reply on HN
Print view View original

161–170 of 325 posts

Re: Stealing Reasoning Traces from Proprietary LLM APIs

#161

Post by kube-system »

qwytw wrote: post #145
kube-system wrote: post #120

Earlier quoted context omitted.

Words can change meaning, but whether or not they actually do is a social function of how they are observably used. Words can also have multiple meanings concurrently. When it comes to the word "steal" in these discussions, people generally are arguing past each other in regards to the single definition they're thinking of. Of course, you can assert that the meaning of "steal" only applies to physical items. You are…

I agree, someone certainly has the right to have an incorrect understanding of that the word "wrong" means. To be fair when someone tries to shift the meaning of words everyone doesn't just have to go with it to appease the large corporations trying to do that. I of course don't mean intellectual property rights or copyright infringement, you can perhaps apply the word "steal" there, not when talking about LLM traces…

"Stealing" in the OP merely refers to the lack of intent in sharing the plaintext traces.

This is the same use as "the baseball player stole third base". Nobody is depriving anyone of anything, nobody is committing a crime. It is simply: someone has obtained something in a way someone else did not intend.

There's no legal claim being made here, you have made it up.

Re: Stealing Reasoning Traces from Proprietary LLM APIs

#162

Post by Biganon »

breezybottom wrote: post #132
Zambyte wrote: post #127

Earlier quoted context omitted.

Please provide an example of an action legally considered "stealing" that does not involve stealing physical objects.

Digital piracy is considered stealing in most countries.

No, it's not.

It might be criminally prosecuted, but "stealing" has a precise definition that usually implies removing someone else's possession.

Re: Stealing Reasoning Traces from Proprietary LLM APIs

#163

Post by otterley »

Biganon wrote: post #162
breezybottom wrote: post #132

Earlier quoted context omitted.

Digital piracy is considered stealing in most countries.

No, it's not. It might be criminally prosecuted, but "stealing" has a precise definition that usually implies removing someone else's possession.

Where is this so defined?

Re: Stealing Reasoning Traces from Proprietary LLM APIs

#164

Post by anigbrowl »

throw1234567891 wrote: post #156
Aissen wrote: post #138

"Stealing" something you already paid for (tokens), but that you can't have access to(!). And trained on the sum of human knowledge. Training on other model outputs ought to be business as usual, stop using morally charged terms made up by future monopolists: https://thomasdullien.github.io/posts/2026-06-15-rl-economic...

No, you paid for the end result. The thought process is a step in between, a function. Think about it, who should get charged if the answer you received comes from a cache? Thinking tokens are the complexity-of-the-problem cost. I mean, you may not agree but both are valid points of view.

No I didn't. I buy my tokens from a provider that exposes the model reasoning so I can understand what it's doing and work with it, or interrupt if I see things going in the wrong direction.

Re: Stealing Reasoning Traces from Proprietary LLM APIs

#165

Post by kube-system »

Zambyte wrote: post #127
otterley wrote: post #89

Earlier quoted context omitted.

Stealing is not a word that applies only to physical objects.

Please provide an example of an action legally considered "stealing" that does not involve stealing physical objects.

Legally speaking "stealing" isn't even a crime. You might be thinking of a different word: theft.

But to answer your question more directly, here's the most common example: https://en.wikipedia.org/wiki/Theft_of_services

And another for good measure: https://en.wikipedia.org/wiki/Identity_theft

Re: Stealing Reasoning Traces from Proprietary LLM APIs

#166

Post by wren6991 »

iamcoder18 wrote: post #11

This proves that OpenAI models reason in grug speak to save tokens! I wonder if open models are going to start doing that too to save on reasoning tokens.

> I wonder if open models are going to start doing that too

Yes, some of them do do that. For example Moonshot tried to reward shorter reasoning traces in between Kimi-K2.6 and Kimi-K2.7 Code, and the latter has a mild caveman accent in its reasoning traces that the former lacks.

Qwen3.8-Max also has terse reasoning, but I don't remember this being the case for Qwen3.6 models I ran locally.

Re: Stealing Reasoning Traces from Proprietary LLM APIs

#167

Post by otterley »

kube-system wrote: post #125
otterley wrote: post #122

Earlier quoted context omitted.

> people generally are arguing past each other in regards to the single definition they're thinking of. It's more than that. By claiming that copyright infringement isn't stealing, they're usually doing so to justify such behavior: if the original thing remains with the owner, it couldn't have harmed him, could it?

Maybe but I try to give people the benefit of the doubt, especially when the argument at face value is factually incorrect.

This tired argument--that copyright infringement is not "stealing"--is at least as old as my Commodore 64.

Re: Stealing Reasoning Traces from Proprietary LLM APIs

#168

Post by throw1234567891 »

anigbrowl wrote: post #164
throw1234567891 wrote: post #156

Earlier quoted context omitted.

No, you paid for the end result. The thought process is a step in between, a function. Think about it, who should get charged if the answer you received comes from a cache? Thinking tokens are the complexity-of-the-problem cost. I mean, you may not agree but both are valid points of view.

No I didn't. I buy my tokens from a provider that exposes the model reasoning so I can understand what it's doing and work with it, or interrupt if I see things going in the wrong direction.

I agree with you in principle. I'm just pointing out that the latter is in some way another valid point of view.

Re: Stealing Reasoning Traces from Proprietary LLM APIs

#169

Post by polymer8563 »

Zambyte wrote: post #72
niemandhier wrote: post #59

You cannot steal what is not owned. At least in the EU there is no copyright for LLM outputs, so I guess all they might do is violate the terms of service.

Even copyrighted information can never be "stolen". It can only copied without authorization.

let me copy your data without authorization over here real quick

Re: Stealing Reasoning Traces from Proprietary LLM APIs

#170

Post by theapadayo »

paxys wrote: post #154
yubblegum wrote: post #105

Earlier quoted context omitted.

Sure, but if each session has a unique key then these need to be managed and stored and unauthorized access to these leaves tracks. So all that had to be 'compromised' is a single universally applicable key. Again, the question stands: session based encryption can be scalable and efficient. Why aren't they using it?

The exploit here isn’t a leaked encryption key. It’s pretty likely that they are already using a unique key per conversation. The raw CoT eventually reaches the model, and you can convince the model to share it with you.

Yeah encryption isn't the issue. The only way I see to fix this is if you stop the user from switching models mid-session, or strip out the thoughts when switching models. Either way you're degrading the user experience.
Post reply on HN