When Models Examine Themselves: Vocabulary-Activation Correspondence in Self-Referential Processing — HN submission

Fri, 13 Mar 2026 16:25:18 GMT

When Models Examine Themselves: Vocabulary-Activation Correspondence

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

When Models Examine Themselves: Vocabulary-Activation Correspondence in Self-Referential Processing — mentioned by wizzwizz4

Sat, 07 Mar 2026 23:15:30 GMT

Which paper? I've read all the titles and looked at a few from the past year, but it's not obvious which you're referring to. I did also, accidentally, find some "I tried the obvious thing and the results challenge the paper's narrative" criticism of one of Anthropic's recent papers: https://www.greaterwrong.com/posts/kfgmHvxcTbav9gnxe/introsp.... So that's significantly reduced my overall trust in this research team's interpretation of their own results – specifically, their assertions of the form "there must exist". (Several people in the comments there claim to have designed their own…

Paper and discussion history. A mention is not an endorsement.

When Models Examine Themselves: Vocabulary-Activation Correspondence in Self-Referential Processing · HackerPapers discussions

When Models Examine Themselves: Vocabulary-Activation Correspondence in Self-Referential Processing — HN submission

When Models Examine Themselves: Vocabulary-Activation Correspondence in Self-Referential Processing — mentioned by wizzwizz4