The decoding tax: latent swarms vs. the pipelines I actually ship

Automated excerpt

Six agents, eleven hops per task, and every single hop does the same dumb thing: a model finishes thinking, renders its internal state into a paragraph of English, and the next model reads that paragraph back in and starts over. Two of those agents exist almost entirely to translate. Hundreds of cheap agents, reasoning in latent space, handing off KV caches instead of sentences, running an evolutionary search loop.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.