GPT user here. Tried Opus 5.5. It’s insane.

A GPT user, who subscribed to Claude after their Codex subscription became unusable, is highly impressed with Opus 5.5. They note that Claude models, including Sonnet 3.5 and Opus 5.5, exhibit an "insanely good" situational awareness that feels almost magical. This user finds Opus 5.5 to be a significant improvement, contrasting it with GPT models which they perceive as more "lobotomized" and overly prompt-driven.