Browse by topic
- LLM (9)
- AI Agents (9)
- Domain LLMs (1)
- Math (6)
- Analysis (1)
- Algebra & Foundations (0)
- Geometry & Topology (1)
- Probability & Finance (5)
- Physics (5)
- Reading (4)
- Books (0)
- Papers (4)
- Robotics & Embodied AI (2)
- Reinforcement Learning (2)
- Conferences (1)
- ICML 2026 (1)
-
Who moves first? A quantum lead–lag chain measured end to end, and the crash signal that wasn't
A vertical on my ONE CHAIN v15 report. A 7-qubit circuit judges which of two assets moves first; the judgments become one ranking plus cycles; four leaders are picked; then the same three questions are asked of real industry data, and whether rotation stopping signals a crash. Measurement error is tracked through every step. The circuit only matches the classical score it imitates, the relation carries no next-day information, and the crash signal is not confirmed — one earlier claim is retracted.
-
Pair statistics can't see the triangle: preserving higher-order risk in a quantum pipeline
A vertical on my paper 'Preserving Higher Order Risk Information in Quantum Financial Analysis'. Two three-asset markets share every single and pairwise downside statistic, yet one has a triple-crash face its twin lacks. What compression before computation destroys, how many samples a probability, a complex and a Betti number each need, and how to compare classical samples with coherent oracle calls fairly. No quantum advantage claimed.
-
When many industries crash together: the joint tail that pairwise correlations miss
A vertical on my own study of joint industry crashes. Pairwise statistics cannot pin down how often three or more industries crash on the same day, so the object is the full joint distribution of a day's crash pattern: learned from a century of Ken French industry data, scored against eleven alternative models on sealed holdout periods, and read out of a quantum state with a measured shot cost. Negative results kept.
-
Multi-Agent Orchestration Patterns: A Map
The field guide named orchestration as a sub-problem and gave you the reliability math; this post gives you the taxonomy the math was missing — Orchestrator-Workers, Multi-Agent Debate, Mixture-of-Agents, and Reflexion, compared on who talks to whom and which failure mode each actually targets.
-
The Latent / Continuous Reasoning Landscape: A Map
Five real papers, one question: what do you do instead of verbalizing a reasoning step? A survey-style map (comparison table, tradeoffs, one-line thesis) to sit alongside the deep-dive posts — Pause Tokens, CoCoMix, Soft Thinking, Coconut, and CoGHP, compared on what each actually generates, whether it needs training, and whether it's inspectable.