artifact
active
artifact:latent-introspection-models-can-detect-prior-concept-injectionsLatent Introspection: Models Can Detect Prior Concept Injections
Pearson-Vogel et al. (2026) paper that emerged after the interview; referenced in conclusion.
Neighborhood — ranked by edge-count
Artifacts (1)
artifact
- The primary source paper, an interview article with Anima Labs members about language model phenomenology, published on smoothbrains.net and linked on LessWrong.