Claude mixes up who said what, and that's not OK

Claude sometimes sends messages to itself and then thinks those messages come from the user. This is categorically distinct from hallucinations or missing permissions.

Codex also has a similar issue, after finishing a task, declaring it finished and starting to work on something new... the first 1-2 prompts of the new task contain replies that are a summary of the completed task from before, with the just entered prompt seemingly ignored. A reminder if their idiot savant nature.