{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreihypgfj3k4odz4k5673eulsqhqkq7fgik4w5f3xhcd57p2f4rfhyy",
"uri": "at://did:plc:pgryn3ephfd2xgft23qokfzt/app.bsky.feed.post/3meqzax2hrmw2"
},
"path": "/t/is-ai-self-aware/173458#post_1",
"publishedAt": "2026-02-13T15:22:59.000Z",
"site": "https://discuss.huggingface.co",
"tags": [
"[2602.11358] When Models Examine Themselves: Vocabulary-Activation Correspondence in Self-Referential Processing"
],
"textContent": "It’s not exactly the hard question.\n\nBut are they self-aware? And how do you measure that, in a transformer model?\n\nMy paper shows that in some ways, models can actually see themselves: [2602.11358] When Models Examine Themselves: Vocabulary-Activation Correspondence in Self-Referential Processing",
"title": "Is AI self-aware?"
}