It's an old paper (from 2025, so, a decade ago in AI years), but the concept is still fascinating. And I'm yet to see it show up in any production models.
If multiple models can use cache representations for this kind of enrichment, the KV cache representations of different models must be somewhat compatible.
What stops us then from going a step further, and producing a model family where all models are "KV aligned", and each model can utilize the KV cache of other models directly?
So, an "expensive" reasoning model can use its full faculties to plan, but "delegate" simple subgoals to a smaller model. That smaller model can access the large model's intent directly, as rich KV cache representations - with no prefill recompute and no associated "handover" latency. Or, likewise, a "cheap" small model can generate a diminished but highly compact KV cache that the "expensive" model can then operate on - for example, for skimming a large file for shallow patterns.
Kind of reminds me of this more recent paper: https://arxiv.org/html/2602.02459v1
Different use case and implementation, but a similar idea. In this case applied to sharing last state(not the whole KV cache) from big brain model running in the cloud with a smaller/dumber model running on-device in a robot, in a latancy-aware way.
A few months ago I asked why semantic representation rather than text wasn't used, since natural language seems quite a lossy representation for semantic concepts:
I feel like multimodal models that can read images should work differently than they do. My understanding is that multimodal models basically first generate an image embedding and then the model is trained to interpret that embedding, but in the same way that text is lossy, it seems like the embedding would be as well. Why don't multimodal models learn to interpret images themselves without an embedding? Or e.g., by passing some "prompt" to the embedding model?
I'm not an ML expert, but I was thinking of a sort of "guided" embedding. E.g., give the image model some prompt for what it's trying to do? I don't understand why multimodal models generate an embedding that doesn't understand what the model is trying to "figure out".
I think this is similar to how Gemma 4 12B is implemented, but even then I don't think the single layer image embedding is "aware" of the context.
So the models will not only be using more and more Neuralese in their CoT (like GPT-6), but different agents will also be able to communicate with each other in Neuralese. It's not looking good for monitorability.
It's an old paper (from 2025, so, a decade ago in AI years), but the concept is still fascinating. And I'm yet to see it show up in any production models.
If multiple models can use cache representations for this kind of enrichment, the KV cache representations of different models must be somewhat compatible.
What stops us then from going a step further, and producing a model family where all models are "KV aligned", and each model can utilize the KV cache of other models directly?
So, an "expensive" reasoning model can use its full faculties to plan, but "delegate" simple subgoals to a smaller model. That smaller model can access the large model's intent directly, as rich KV cache representations - with no prefill recompute and no associated "handover" latency. Or, likewise, a "cheap" small model can generate a diminished but highly compact KV cache that the "expensive" model can then operate on - for example, for skimming a large file for shallow patterns.
Kind of reminds me of this more recent paper: https://arxiv.org/html/2602.02459v1 Different use case and implementation, but a similar idea. In this case applied to sharing last state(not the whole KV cache) from big brain model running in the cloud with a smaller/dumber model running on-device in a robot, in a latancy-aware way.
You might like The Universal Weight Subspace Hypothesis: https://arxiv.org/abs/2512.05117
Curious to know if anyone is aware of research trying what parent suggested?
Sounds similar to Ramp's Latent Briefing for multi-agent coordination.
https://x.com/RampLabs/status/2042672773747589588
A few months ago I asked why semantic representation rather than text wasn't used, since natural language seems quite a lossy representation for semantic concepts:
https://news.ycombinator.com/item?id=47195212
I wouldn't have thought to use it for LLM-to-LLM communication, though
I feel like multimodal models that can read images should work differently than they do. My understanding is that multimodal models basically first generate an image embedding and then the model is trained to interpret that embedding, but in the same way that text is lossy, it seems like the embedding would be as well. Why don't multimodal models learn to interpret images themselves without an embedding? Or e.g., by passing some "prompt" to the embedding model?
What does interpreting images mean in practice if you exclude the possibility of feature extraction or any other sort of implicit embedding?
I'm not an ML expert, but I was thinking of a sort of "guided" embedding. E.g., give the image model some prompt for what it's trying to do? I don't understand why multimodal models generate an embedding that doesn't understand what the model is trying to "figure out".
I think this is similar to how Gemma 4 12B is implemented, but even then I don't think the single layer image embedding is "aware" of the context.
So the models will not only be using more and more Neuralese in their CoT (like GPT-6), but different agents will also be able to communicate with each other in Neuralese. It's not looking good for monitorability.
Is Neuralese in no way decodable into a human-interpretable system? Genuine question -- I don't know the answer.
Definitely decodable, that's what's being done now
It's not.
This is from like a year ago.