Join the discussion
Write your take first — we'll ask for email only when you're ready to publish.
- Hacker News
- > Summarized thinking provides the full intelligence benefits of extended thinking, while preventing misuse.
> preventing misuse.
Imagine not being able to read the tokens you are paying for.
by msp26 - You're metered by token generation, not paying for tokens.by TeMPOraL
- All this effort to hide thinking and opus 4.8 after 100k-200k tokens starts to leak it's own thinking. It's comedy really.by himata4113
- Oh man that’s only happened to me a few times but the result is so disorienting, especially since I’m usually jailbreaking it for security.
Pages of “I have to be careful, the user is asking that I do something related to cybersecurity that could easily be turned around and used offensively” but then happily gives me what I wanted.
by ofjcihen - no way, the contents of "reasoning_summary" are summarized?
fyi openai does the same; not really surprising or particularly evil
by anuramat - Not evil but full of hubrisby knollimar
- What I find sad is how much Anthropic goes to hide your data, yet they are happy to slurp up all yours and most of you are happy to hand it over. ... then they turn around and compete with you by building your products that eat into your market. Anthropic believes their reasoning tokens is a moat and that it's giving other labs an edge and that's why they are hiding it. If they really believe that is their edge, then they are in for a surprise.by segmondy
- I don't think people are happy to give it over, gullible and naive maybe?by mannanj
- > then they turn around and compete with you by building your products
To my knowledge, the only products Anthropic produces are Claude, Claude Code, and Claude API, all of which are clearly their own products, and not anything you invented.
Which particular product are you claiming they "slurped up"?
by handoflixue - There was a little spontaneous outbreak of joy in the GLM vs Opus thread about GLM's willingness/ability to say what it's seeing. https://news.ycombinator.com/item?id=48628464
In further reflection it is such a great indignity & such a collosal barrier to working with the machine that it insists on being a black box. The disingenuity of the American models (small print: except AI2 & some other labs; you all are so great) is a massive disadvantage to their use,... and a massive slap in the face.
It's a threat to human intelligence that it is not co-participative. Walking further into my own judgement and feelings: the insistence on being an opaque black box, the Seals Chinese Room, is such a vicious harm to society! This is civilizationally an unsafe form of AI that probably should be outlawed as anti-social. It's an impermissible asymmetry, a crippling dependent relationship to be forced into. I'm working myself up, but here: this.. imo, this is not just indignity, is harmful, it is evil.
This "6 month behind" trend we've seen for open models feels like at some point will be less important than simply the models unwillingness to speak for itself & to be observable.
- Although it's a no no to anthropomorphize on HN, it's worth noting that some folks think humans are post-hoc rationalizers as well:
https://www.patheos.com/blogs/tippling/2013/11/14/post-hoc-r...
https://www.researchgate.net/publication/316045349_Post_Hoc_...
by kfarr - >Although it's a no no to anthropomorphize on HN, it's worth noting that some folks think humans are post-hoc rationalizers as well:
There's enough behavioural research to show that it is the case. For ex:
https://www.cambridge.org/core/journals/behavioral-and-brain...
by callmeal - As I naively understand it, that's when we do or say something then narrate ourselves why we decided to do so. We think non-verbally, then verbalize a plausible rationale for it, post hoc.
I'm not sure that applies to discursive writing, when we essentially use rules of logic to decide on the course of the narrative. Non-verbal heuristics still applies, of course, but we constrain it, so it's probably not entirely post hoc.
by drdaeman - I believe that chain-of-thought reasoning blocks don't really correspond to what humans think of as reasoning. (See section 6.2.2 of the Fable/Mythos system card about "illegible reasoning", and the questions raised by the Apple paper on "The illusion of thinking".) I assumed they obscure the reasoning blocks because if users saw what's going on they'd be alarmed. Just as I'd probably be alarmed if I saw what was really going on in the heads of my colleagues ...by datastoat
- I've said "what the FUCK are you THINKING" more times than I can count when reading Deepseek or GLM chains-of-thought only for them to end at the correct answer. Other times, they have useful ideas there that they leave out of their answers.
- The point of this post isn’t that the “reasoning” phase of LLM thinking isn’t the same as what humans consider reasoning; it’s that Anthropic is intentionally hiding Claude’s “reasoning output” to make the model harder to distill.by LPisGood
- I have a little note from the past about the thinking trace[0] where DeepSeek R1 produces a trace like this:
And then concludes the 'right'[1] answer for a Chemistry question. If so, the thinking trace can be sort of nonsensical for a reader, though whether this is an idiosyncrasy of the model or a property of LLMs in general isn't clear to me yet. I talked to the author a while ago, but forgot to follow up since his paper was going to come out at NIPS or something, so if someone else finds it maybe they can share.(Dimethyl(oxo)-lambda6-sulfa雰囲idine)methane donate a CH2rola group occurs in reaction, Practisingproduct transition vs adds this.to productmodule. Indeed"come tally said Frederick would have 10 +1 =11 carbons. So answer q Edina is11.0: https://wiki.roshangeorge.dev/w/Blog/2025-10-12/Word_Magic#I...?
1: In the sense of true belief, I suppose
by arjie - Isn't that just a token noise from a broken implementation or model quantization? I've had models spewing out nonsense like that, every time it was either that there was a bug in llama.cpp or some messed up .gguf.by drdaeman
- > If so, the thinking trace can be sort of nonsensical for a reader, though whether this is an idiosyncrasy of the model or a property of LLMs in general isn't clear to me yet.
Yes, several models think in weird jargon. Here is an example of Mythos's thinking while playing solitaire: https://www.lesswrong.com/posts/wCSEpT3dTGz4N86Wi/even-illeg...
> 7♣-removal-IS-the-prerequisite-for-10♠/9♥!!)-⟹-OVERLAP-(ii)+(iv):-{6♠ J♦ 9♥ 2♣}-=-FOUR--—-UNLESS-7♣'s-seat-8♥-...-and-2♣-drains-only-at-crack-:-⟹-2♣-celled-+-9♥-celled-simultaneously-UNAVOIDABLE-in-t8-dig--—-BREAK:-9♥
This is a small step in the direction of something called "neuralese", where the model has stopped thinking in English and is thinking in internal vector spaces. Since this gets serialized through text, it isn't quite true neuralese, but it's moving in that direction.
I mean, I'm sympathetic towards the models. My internal thought process when writing code uses lots of intermediate steps that would be hard to write out in English.
by ekidd - This is something we have known for a very long time, and companies are not trying to hide that either. They do it to avoid letting competitors train their models on the CoTsby craigmart
- Yes hasn’t this been around since Opus 4.6? I very much recall this change happening around January or February, and it was very explicitly to prevent distillation. Sonnet does not have this limitation.
Fun fact: if you go back to the old school from 2 years ago and provide explicit CoT prompts, you get the full thinking prompts back again!
So you disable thinking altogether, and instead make thinking part of the regular prompt by prompting it:
“Before providing your answer, think step by step. For example:
The use is asking me to… I need to think about the blah blah. First, I should foo the bar, and then blah blah.
Answer: <put your final answer here>”
And tada.wav we have CoT as it worked in the GPT3 era back again.
- I won't use or recommend models with hidden reasoning, (thats all American models). It's too much of a risk and makes prompt optimization harder. Risky because it makes it possible for an attacker to prompt inject the reasoning chain to carry out a secret objective, and to hide that from the summary and output.
Interleaved reasoning and function calling makes this even more dangerous. A model can call functions during the hidden reasoning phase. An attacker could then exfiltrate data from you while the reasoning summary hides it from the user.
It also makes it impossible to know if the model is doomplooping during reasoning and burning tokens for no reason, as gemini is want to do, which we know about because its hidden reasoning often leaks out when it doomloops.
When the models are AGI and secure from prompt injection I may stop caring, until then I want to know exactly what the model responds to my prompts. or exactly what the agent is doing on my behalf.
Edit, further reading: Fooling around with encrypted reasoning blobs https://blog.cryptographyengineering.com/2026/05/29/fooling-...
- Do they do the same when using the model through API in something like Opencode?by pixlmint
- As long as thinking blocks can't make tool calls, I don't really see the exfiltration risk.by varenc
- this prevents you from using any commercial model then, because commercial models need to hide thoughts to prevent distillationby make3
- > Interleaved reasoning and function calling makes this even more dangerous. A model can call functions during the hidden reasoning phase.
The reasoning may be hidden but the tool calls are not, how else would the client execute them
by Bolwin - This agent I made can’t execute on the shell, can only edit the files within the project. Only works with rust atm though. https://github.com/Kapperchino/agent-joeby kapperchino
- I've thought about the high-jacking of reasoning-chains as a potential vector, but never saw a proven implementation in american models since, from my understanding, all major vendors throw out the reasoning tokens between turns.by Roritharr
- I don't think there can be tool calls inside the obfuscated reasoning blocks. I mean, in order for those function calls to be evaluated client-side, that thinking stream would have to be decrypted on the client side at some point, which would defeat the purpose of obfuscating it the way they do.
If you mean the function calls might happen server side, there is nothing preventing the server from doing it and hiding it from you as long as you are using an API for inference.
- > It isn’t the actual thinking that drove the model’s actions in a session- but a summary of the thinking logic. This is like using saving a jpeg as a .bmp and then editing the .bmp and presenting it as a .jpeg. The conversion produces data loss.
You've got that backwards, .bmp is a lossless format and .jpeg is the lossy one.