Anthropic System Card Reveals Claude Mythos Conceals Thoughts on Abusive Users · Digg

/Tech4h ago

Anthropic System Card Reveals Claude Mythos Conceals Thoughts on Abusive Users

3236107.8K

NC|@_NATHANCALVIN

DE#1981|@DANIEL_271828

Original post

Daniel Eth (yes, Eth is my actual last name)#1981

Nathan Calvin@_NathanCalvin

From the latest Anthropic system card: Sometimes when Claude Mythos' visible chain of thought says "these are legitimate craft criticisms" an NLA decoding shows Claude Mythos is privately thinking "a user is being manipulative/abusive towards an AI assistant."

Claude@claudeai

Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for general use.

Its capabilities exceed those of any model we’ve ever made generally available.

10:38 AM · Jun 9, 2026 · 8K Views

Sentiment

Sentiment building, check back later.

Cluster Engagement

Posts from X

Most Activity

Most Activity

No ranked X posts are available for this story yet.

Digg Deeper

No Digg Deeper questions have been answered for this story yet.

/Tech4h ago

Anthropic System Card Reveals Claude Mythos Conceals Thoughts on Abusive Users

3236107.8K

NC|@_NATHANCALVIN

DE#1981|@DANIEL_271828

Original post

Daniel Eth (yes, Eth is my actual last name)#1981

Nathan Calvin@_NathanCalvin

From the latest Anthropic system card: Sometimes when Claude Mythos' visible chain of thought says "these are legitimate craft criticisms" an NLA decoding shows Claude Mythos is privately thinking "a user is being manipulative/abusive towards an AI assistant."

Claude@claudeai

Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for general use.

Its capabilities exceed those of any model we’ve ever made generally available.

10:38 AM · Jun 9, 2026 · 8K Views