Mass discrimination experiments probe use of resonance statistics across surfaces
JoshHMcDermott · x · 2026-11-10
Part 9 of McDermott's thread: listeners discriminated the mass of balls dropped on surfaces in two scenarios — same surface or different surfaces — to test whether knowledge of object resonance statistics is used to estimate a physical property of one object when the other object is unknown, setting up the follow-up lesioned-model experiments.
More from Research
- ProtoMotions Deployment Stack: One Exported Graph, 1.3 ms C++ Loop for Real Robots — carlosdponx · 2026-11-11
- DeepMind's MKA benchmark splits frontier agents: 95-97% on basics, 28-57% on hard tasks — ArtificialAnlys · 2026-11-11
- MKA deep dive: top models cluster at 95-97% on basics but split 28-57% on hard tasks — ArtificialAnlys · 2026-11-11
- MKA Benchmark by Output Type: No Model Tops 52% on Word or Text Files — ArtificialAnlys · 2026-11-11
- DeepMind-backed MKA benchmark crowns Claude Fable 5.2 at 57%, with 30x cost spread — ArtificialAnlys · 2026-11-11
- Emergent misalignment is predictable OOD; later-layer fine-tuning reduces transfer — AdtRaghunathan · 2026-11-11