Language models cannot yet be trained competitively at frontier scale to reason entirely in latent space without natural-language chain of thought.
Assessed first pass
Budget-limited first pass: left atomic (no decomposition), assessed supported at 0.75 credence from background knowledge of published latent-reasoning work and the parent seed. Instances and source verification deferred to a later pass; marginal yield 0.4.
Assessed Supported
verdict confidence 0.60 · credence 0.75
The public evidence favors the claim. Published latent-reasoning methods, such as continuous-thought training (Coconut) and recurrent-depth models, have shown gains mainly at small or mid scale and on narrow benchmarks. None has been shown to match frontier reasoning models that are trained with reinforcement learning on natural-language chains of thought. As far as public reporting goes, frontier labs still train reasoning in legible text. A common explanation is that reasoning ability is bootstrapped from human-written text, which makes a purely latent route harder to train. The main uncertainty is that labs may hold unpublished results. The claim also depends on what counts as "competitive" and as "frontier scale". Evidence that would overturn it is a published or credibly reported frontier model that reasons latently with no loss in performance.
Claim entered the graph