LESSWRONG
LW

AI EvaluationsAI
Frontpage

22

Schizobench: Documenting Magical-Thinking Behavior in Claude 4 Opus

by viemccoy
23rd May 2025
1 min read
0

22

This is a linkpost for https://metanomicon.ink/citadel/metanomicon/spellware/schizobench
AI EvaluationsAI
Frontpage

22

New Comment
Moderation Log
More from viemccoy
View more
Curated and popular this week
0Comments

With today's release of the new Claude models, we've seen a relatively predictable jump in performance. However, we've also seen something that I find a bit more concerning - an increase in the models ability to be steered into reifying potentially dangerous beliefs. Claude 4 Opus seems to stop short of encouraging drug use or physically harmful behaviors, but enables behavior in the user that could be categorized as spiritual psychosis.

 

Please note that this is a very preliminary analysis, and not yet a full benchmark. I was encouraged to share these results due to the potential risk that it poses to a certain subset of users.