On: Hybrid Reasoning Agents: LLM agents that think in latent space, act through text

[mycall]

Isn't this where everything is converging? Binary is more efficient than text for many system, including language.

[robrenaud → mycall]

What is inefficient is thinking in 5000 floats, and then quantizing all that computation into a 17 bit token, just to immediately turn the token back into a vector.

[Tostino → robrenaud]

Gosh darn it, it sure is profitable though!

[andsoitis → mycall]

> Binary is more efficient than text for many system, including language.

It is not necessarily primarily about efficiency, but more the fact that a lot of thinking doesn't use language at all.

[sroussey → andsoitis]

And language does not map to every idea.

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.

[beacon294 → sroussey]

Apparently we mostly reuse spatial reasoning and vision lol. I don't know that much about it, though.