Skip to content
Topic

#Llm Interpretability

1 article on Llm Interpretability — news, releases, guides and analysis from the SourceFeed engine.

Claude Notices Its Own Thoughts, 20% of the Time
Article 2h ago 0

Claude Notices Its Own Thoughts, 20% of the Time

Anthropic's concept-injection experiments finally give model self-reports a ground truth, and a reality check.

Mariana Souza