Gareth Dwyer personal blog

Claude mixes up who said what

Claude sometimes sends messages to itself and then thinks those messages come from the user. This is categorically distinct from hallucinations or missing permissions.
Points
467
HN comments
360
Submissions
1
Cited by
0 commenters

AI & Machine LearningSociety, Policy & Culture2026

On Hacker News

SubmittedTitle on HNPointsComments
Apr 9, 2026Claude mixes up who said what by sixhobbits467360

More from Gareth Dwyer

All 3 posts →

Related posts from the same era