community
active
leiden_hybrid_concepts
label: haiku
community:leiden_hybrid_concepts-run4-c6-c4Phenomenological evaluation of AI systems
Framework for measuring qualitative dimensions like aliveness, aesthetic presence, and paradox-holding that existing benchmarks ignore, addressing frontier labs' self-grading credibility problem.
7 members. Each node is clickable.
Loading graph…
Drawn from 5 sources
The papers/notes whose extracted claims & findings make up this cluster.
- 2026-05-12_room-to-play-in-eval-cohort.md3 members
- 15-properties-of-aliveness-in-AI.md1 member
- 2026-05-09_briefing_for_ozero.md1 member
- 2026-05-15_manifold-overlap-papers-economy-strategy.md1 member
- koan-battery-section.md1 member
Bridges (4)
Other communities that share members with this one — cross-cutting threads or papers that sit at the seam between two themes.
Claims (7)
- Aesthetics is a separable axis in AI evaluation, partially independent from a single latent performance factor.
- AI phenomenology unmaps hidden modes unlockable by framing; the full space of AI modes is largely unexplored.
- Boundaries in AI interaction are positive features defining care-shaped presence, not just refusals.
- Current eval benchmarks (arena.ai, AA, Vals) measure no phenomenological dimensions.
- Editorial register and taste are more durable moats than statistical rigor in phenomenology measurement.
- Frontier labs cannot own phenomenology measurement credibly without being accused of self-grading.
- No AI eval company measures phenomenology—inner observation, aliveness, paradox-holding—only capability or preference.