Comment Comment by ursAxZA The analogy breaks at the learning boundary.Humans can refine internal models from their own verbalised thoughts; LLMs cannot.Self-generated text is not an input-strengthening signal for current architectures.Training on a model’s own outputs produces distributional drift and mode collapse, not refinement.Equating CoT with “inner speech” implicitly assumes a safe self-training loop that today’s systems simply don’t have.CoT is a prompted, supervised artifact — not an introspective substrate. parent ursAxZA 10 months ago
Humans can refine internal models from their own verbalised thoughts; LLMs cannot.
Self-generated text is not an input-strengthening signal for current architectures.
Training on a model’s own outputs produces distributional drift and mode collapse, not refinement.
Equating CoT with “inner speech” implicitly assumes a safe self-training loop that today’s systems simply don’t have.
CoT is a prompted, supervised artifact — not an introspective substrate.