Le Corbusier. Ronchamp

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• The images created by famous architects (Le Corbusier, Mies, etc.) formed an accepted style that embodied defects of the production system and became targets for younger architects.claim0.700
  Image propagation in architectural culture.
• Claude 4 Opusconcept0.685
  Anthropic model; outlier in Experiment 1 with high baseline affirmation including under zero-shot and history conditions
• Claude Opus 4 and 4.1 exhibit the greatest degree of introspective awareness among tested modelsclaim0.673
  Based on consistent best performance across experiments.
• Notably, Claude Opus 4.1 and 4—the most recently released and most capable models of those that we test—perform the best in our experiments, suggesting that introspective capabilities may emerge alongside other improvements to language models.quote0.672
  Key finding about the relationship between capability and introspection.
• Erwin Schrödingerthinker0.671
• Claude Opus 4.6 represents a plan to end a couplet with 'rabbit' before outputting the rhyming line.finding0.669
  Demonstrates causal relationship between NLA explanations and model outputs via steering with edited explanations.
• Eckert, Pabst, and Endres 2022concept0.668
  Source of the HMM parameters for normal and chronic pain models used in this paper
• RoBERTaconcept0.667
  Masked language model used in color cooccurrence experiment to represent predictive language learners