Published on February 13, 2026 3:30 PM GMTIt’s not exactly the hard question.But are they self-aware? And how do you measure that, in a transformer model?My paper shows that in some ways, models can actually see themselves: [2602.11358] When Models Examine Themselves: Vocabulary-Activation Correspondence in Self-Referential ProcessingDiscuss Read More
Is AI self-aware?
Published on February 13, 2026 3:30 PM GMTIt’s not exactly the hard question.But are they self-aware? And how do you measure that, in a transformer model?My paper shows that in some ways, models can actually see themselves: [2602.11358] When Models Examine Themselves: Vocabulary-Activation Correspondence in Self-Referential ProcessingDiscuss Read More
Related Posts
What’s Your P(WEIRD)?
Published on February 16, 2026 6:19 PM GMTEpistemic status: the other thing that keeps me…
Carrot-Parsnip: A Social Deduction Game for LLM Evals
Published on February 20, 2026 11:06 PM GMTSocial Deduction games (SD games) are a class…
Increasing AI Strategic Competence as a Safety Approach
Published on February 3, 2026 1:08 AM GMTIf AIs became strategically competent enough, they may…