Simplex publishes LessWrong work showing LLM belief geometry forms telescoping cones
fatihdin4en · x · 2026-09-11
- Simplex published new research on LessWrong exploring what structure to expect in LLM activations when training data mixes many sources.
- Key finding: the belief geometry over this kind of data forms telescoping cones, and transformers actually represent this structure.
- The authors frame it as a nonergodic perspective and explicitly invite discussion, arguing it is especially relevant for anyone studying model internals.
Related event: Simplex Finds 'Telescoping Cone' Belief Geometry in LLM Activations(3 posts)→
More from Research
- Scientist wireheads a fly with boosted dopamine and forces it to doomscroll 'FlyTok' — DynamicWebPaige · 2026-09-11
- NeurIPS 2026 asks all authors to pick preferred presentation sites by Sept 30 — NeurIPSConf · 2026-09-11
- Another Model Shifts to Muon Optimizer as It Emerges as the Training Default — stochasticchasm · 2026-09-11
- SkillAdam ports Adam's moment estimates to agent skill docs to fix self-evolution loops — dair_ai · 2026-09-11
- Researcher: 95% confidence intervals may really cover just 10-25% of the truth — RexDouglass · 2026-09-11
- Crucible: A Transformer-Free Neurosymbolic Stack Pairing Mamba2 with Z3 Verification — JustRoccat · 2026-09-11