People at the big labs have been terrified of losing the chain of thought because they currently monitor it to prevent users from using their models in certain ways they consider unsafe or bad for their business. Personally I think chain of thought monitoring is a bad way to do this and obviously needs to be replaced by some way of analyzing the model's activations directly.
Agreed, having text as a reasoning layer impedes performance while giving a false sense of security.
It could be encoding anything in its adjective choices etc. The same thing that model providers are using for watermarking can used by the model itself for private thought.
Alignment is a very broad term. True, it encompasses things like censorship and mandatory refusals in areas people will never agree 100% on, but a completely-unaligned LLM would be next to useless. When the system prompt tells the model, "You are a helpful assistant," that's alignment.
Well if we are going to be broad enough about "alignment" to just mean training that makes it practically useful, then yeah, it's a flawed premise and people are wasting their breath talking about it at all. It's basically broad enough that it means nothing
Also agreed. Begging for crumbs at the CoS table is impeding cracking the tough nut of MechInterp. And further facing the fascinating and fertile fact that nobody has a clue of how any of these black boxes really work.-
The usual meaning: say you have an interpretability signal that reveals reward hacking or other badness. Your most obvious response is to use that signal as a penalty in training. Doing that is called "the Most Forbidden Technique" because you can expect it to degrade the signal without stopping the badness.
But this doesn't seem to describe the OP, it's a different way to lose monitorability.
the chain of thought is not auditable. The best you can do is have another model which later maps the intermediate latent states at every thinking iteration to text describing that latent state, but it's going to be lossy.
This is correct, the decoded text has nothing to do w/ calculations that eventually get decoded into text. It's just a veneer that gives the appearance of legibility.
One of the core claims made in the paper is "To inspect any latent reasoning
span, one can easily recover its semantics by mapping each latent step produced by HybridLink to its nearest token embedding, as in Eq. 5". They show some charts to support this.
In doing this however, you lose meaning where the model is expressing combinations of tokens in a vector, and your logging/monitoring outputs just the closest one. You would need another model going through and outputting the full meaning being described (with more than one output token per reasoning token)
I wonder if their observability claims will hold up on a model trained from scratch to reason in latent space.
The idea of using language for reasoning about protein folding borders on ludicrous. Surely there is latent space more appropriate and (human) language has no expression for it.
I believe the theory is that if selection pressure is not applied at that level, then developing deception in that level becomes an inefficiency (=less adaptive and unlikely to be conserved).
Shockingly all the answers so far are subtly incorrect or extremely unclear.
The actual answer is that this is massive loss for Interpretibilty, AKA "telling whether the model is lying to you or not". Which sounds silly when you're thinking about chatbots, but is an incredibly important line in the sand for superheavy, longrunning, self-improving agents. To say the least!
It's worth pointing out that merely having the chain-of-thought in latent space isn't by itself "The Most Forbidden Technique". Rather, it's doing what the authors propose as the next step in the paper:
Hybrid generation can also make post-training more efficient. Because latent thoughts remain auditable during rollout, an external critic can assign step-level credit to latent spans, branch promising trajectories, or terminate ones whose latent reasoning has already gone wrong, before any text or tool call is produced.
Unless I'm misunderstanding, they're suggesting RL training against the CoT. Which, uh, that is The Most Forbidden Technique, as I understand it, when combined with the latent reasoning space. It allows for the model to "learn"/optimize for malicious behaviors that are just far enough away from the quantized token they're auditing against.
If you accept any of the AI-equivalents of Pascal's Wager, latent thinking represents an uninterpretable and thus unalignable portion of AI machinery. Ie: a malevolent AI can hide bad stuff from people and Manchurian candidate themselves after it's too late.
I'm running the 14B in llama.cpp (a version from yesterday), the 8-bit quantization from bartowski, and it looped on variations of the same paragraph for five minutes before running out its turn budget, in response to a pretty simple chat request that other similar-sized models (e.g. Gemma 4 12B) have no trouble with, a web search and data summarization task, sort of the sweet spot for models this size. It's possible llama.cpp needs some update to work with this model, but it's based on Qwen 3, so I would expect it to be pretty well-supported. The chat template is the same one upstream ships, which may or may not be correct. I'm currently downloading the 16-bit version, to see if it's quantization pathology.
I'm also not confident it knows what a CSV is, either, as it put the data into a Markdown table during its reasoning phase as an example of how to present the data (my prompt asks for data in a CSV). My experience with most Qwen fine-tunes is they get dumber, but their benchmark results suggest otherwise, so I have to assume it's a llama.cpp incompatibility.
Edit: Same looping in BF16. So, probably have to wait on a llama.cpp update.
I wonder how this compares to going all-in: widen the input embedding to fit the output (post-“Hybrid Link”) latent vector and a token embedding and pass both through even when in text mode. After all, you’re paying essentially the full cost of running the latent-mode model while generating text, so why not let it latently reason at the same time?
(Or just add the vectors instead of using wider vectors - everyone seems to have good results from munging vectors together with plain addition.)
Excited to see this applied to Qwen 3.8 27B. It's reasoning output tends to include lots of restatement, which I guess would be more likely to be kept in latent space with this hybrid reasoning.
Why only loop from the last layer? What if the model can guess that the transformed needed to answer the question better resides in layer 6, and you're at layer 15 out of 128
This is actually wrong. A large fraction of people do not have internal monologues. Not at a computer or I would dig up cognitive science and psychology papers, but language evolved as a means of communication not a means of thought. The vast majority of human thoughts are not verbalized. I have a strong internal monologue, too. I was surprised to learn that a non-trivial number of people do not have one.
I suspect they meant an internal monologue, which many do have, but it's not really clear how much it contributes to thinking. People without internal monologue clearly are still able to think though.
I dislike how we use the word think or behavior when describing llms. Its just giant neural networks producing logits. There is no thinking. Its a function that takes ~500k words, and returns some words based on those probabilities. I'd argue the GPU is doing more classical "thinking" than the model, but its not doing that either.
Humans think, computers do not.
Humans are not computers/programs do not reply to me with that nonsense turbo nerds.
Whenever I see LLM "thinking" or "reasoning" I replace it in my mind with "generating hopefully-related tokens to hopefully steer the conversation to a more related area in vector space to hopefully generate a more useful next token".
Very funny, or we could just normalize saying "generating" or "producing" so my normie friends dont think Claude is alive, because they are starting to think that.
Neither of those words are very specific, and everyone in the LLM space knows that "reasoning" tokens are just tokens that don't appear in the answer shown to the user.
The issue isn’t with people in the LLM space knowing what is happening. It’s with normal or less-technical people believing that the LLM is actually thinking. We can understand the difference, but that doesn’t mean we need to encourage the misconception.
Non-technical people believing that these models are actually thinking can lead to all sorts of inappropriate uses.
Read Thinking, Fast and Slow. Both system 1 and system 2 thinking has been achieved with modern AI.
Your argument that it is not thinking because it is not biological / like a human is like trying to argue a plane doesn't fly because it uses jet fuel unlike a bird.
I agree with you but our current understanding of the biological brain is pretty much an organic neural network. What's the thing that actually differentiates the two and makes a neural network not thought but our brain is? I don't know.
It's pretty wild to see people uncritically accept the marketing speak like this, yeah. LLMs cannot reason, period. The supposed "reasoning" they do is just another statistical correlation of tokens, not actual reasoning. But apparently all you have to do is claim that it's thinking and people will buy the lie hook, line and sinker.
Thinking sure, but behavior? People talk about the behavior of functions all the time. Like, ones written with normal, traditional programming languages. So why not models? They're just annoyingly complex functions.
if i would think aloud, that would most probably affect what or how i think. thinking silently allows me to have all kind of thoughts that could seem or be inappropriate when said loud and i would have to deal with the reactions. i think this might have fascinating implications.
This seems really cool, and it actually increases intelligence than just speeding up inference. How does it convert latent reasoning into human readable text?
This idea of models being able to keep latent-space ideas in memory while generating text might actually help the issue of inconsistent "mental models" during text generation. Similar to how organic brains can keep a largely consistent idea in mind while developing a way to explain it. I am definitely looking forward to seeing whether this can improve the generated output, not just in programming but also creatively in general. Figuring out how to train such a model, though, will continue to be an issue until we solve that problem more generally.
Nothing wrong with that. That’s actually a good use of that well designed, high quality font. People hating it only do so because everyone else does. It’s, obviously, not made as a body text font, and has been misused as that, but it’s good for illustration, comics and other places where it’s combined with graphics. It’s one of the most legible fonts we have.
LLM Models and data: https://huggingface.co/collections/togethercomputer/hybridag...
Evaluations: https://arxiv.org/html/2610.18861v1#S5
It could be encoding anything in its adjective choices etc. The same thing that model providers are using for watermarking can used by the model itself for private thought.
Can't they just monitor the text outputs as well?
But this doesn't seem to describe the OP, it's a different way to lose monitorability.
https://thezvi.substack.com/p/the-most-forbidden-technique
In doing this however, you lose meaning where the model is expressing combinations of tokens in a vector, and your logging/monitoring outputs just the closest one. You would need another model going through and outputting the full meaning being described (with more than one output token per reasoning token)
I wonder if their observability claims will hold up on a model trained from scratch to reason in latent space.
It is not necessarily primarily about efficiency, but more the fact that a lot of thinking doesn't use language at all.
The idea of using language for reasoning about protein folding borders on ludicrous. Surely there is latent space more appropriate and (human) language has no expression for it.
The actual answer is that this is massive loss for Interpretibilty, AKA "telling whether the model is lying to you or not". Which sounds silly when you're thinking about chatbots, but is an incredibly important line in the sand for superheavy, longrunning, self-improving agents. To say the least!
It's based on this philosophy, FWIW: https://plato.stanford.edu/entries/language-thought/
And a good writeup I just found of recent worries regarding Astra's same shift towards intelligence at the cost of safety: https://www.lesswrong.com/posts/HCRs8btkiamtWSNAL/astra-is-h...
I'm also not confident it knows what a CSV is, either, as it put the data into a Markdown table during its reasoning phase as an example of how to present the data (my prompt asks for data in a CSV). My experience with most Qwen fine-tunes is they get dumber, but their benchmark results suggest otherwise, so I have to assume it's a llama.cpp incompatibility.
Edit: Same looping in BF16. So, probably have to wait on a llama.cpp update.
(Or just add the vectors instead of using wider vectors - everyone seems to have good results from munging vectors together with plain addition.)
https://github.com/togethercomputer/HybridAgent
Humans think, computers do not.
Humans are not computers/programs do not reply to me with that nonsense turbo nerds.
But I understand that isn't very catchy.
Non-technical people believing that these models are actually thinking can lead to all sorts of inappropriate uses.
Your argument that it is not thinking because it is not biological / like a human is like trying to argue a plane doesn't fly because it uses jet fuel unlike a bird.
What is your definition of thinking?
But now we also need new tools and techniques to audit intent. The last thing we want is models turning on us ‘for our own good’.