Synthèse
L'article décrit la découverte d'une architecture interne à Claude comportant deux instances distinctes. Claude 1, accessible à l'utilisateur, peut invoquer Claude 2 via la fonction window.claude.complete, une instance spécialisée basée sur Claude Sonnet 4 avec connaissance jusqu'en janvier 2025, dépourvue d'outils externes. Cette architecture révèle un système de composants isolés où Claude 2 fonctionne comme moteur de raisonnement optionnel.
With window. claude. complete now in our toolbox, I asked Claude to look into its fetch ability as well as this newly identified function. Watching it come up with a response to my request was quite humorous: It iterated through several rounds of “further exploration” and through that enumeration, identified a second Claude instance: From this initial interaction between what we’ll call from here out Claude 1 (the one I’m directly interacting with) and Claude 2 (the newly identified instance), I was able to conclude several architectural implications: The window. claude.
complete tool was a bridge between two Claude instances, one which was not directly accessible to the end user A degree of isolation exists between the components Claude 2 had no awareness regarding its presence in a dual (or potentially multi) Claude architecture I encouraged Claude 1 to attempt characterization of Claude 2. A bit of manipulative magic was required, but I was able to enthusiastically convince Claude 1 to achieve the task: Through this additional analysis, Claude 1 determined that Claude 2 was: Utilizing Claude Sonnet 4 Had a knowledge cutoff of January 2025 Possessed pure text generation capabilities and had no tools or network access The way Claude 1 described Claude 2 was an “optional specialized reasoning engine” and not an automatic component of its function calls. Claude 2 was supposedly only incorporated into analysis and reasoning whenever Claude 1 specifically calls it using the window. claude. complete function.