technocracy

Every investor talks about risk, but few can explain what truly drives it. We measure volatility, beta, or max drawdown, and assume we understand exposure. Yet these numbers are only outcomes. They tell us how much pain existed, not why it happened. Sometimes a high P/E stock crashes harder. Sometimes a low-margin business stays resilient. Correlation alone can’t answer what actually causes those reactions. That’s where most models stop, and where this story begins. This experiment tries to […]

Ver mais

In this work, we propose a notion of practical learnability grounded in finite sample settings, and develop a conjugate learning theoretical framework based on convex conjugate duality to characterize this learnability property. Building on this foundation, we demonstrate that training deep neural networks (DNNs) with mini-batch stochastic gradient descent (SGD) achieves global optima of empirical risk by jointly controlling the extreme eigenvalues of a structure matrix and the gradient energy, and we establish a corresponding convergence theorem. We […]

Ver mais

The fundamental tension in conversational AI has always been a binary choice: respond fast or respond smart. Real-time speech-to-speech (S2S) models — the kind that power natural-feeling voice assistants — start talking almost instantly, but their answers tend to be shallow. Cascaded systems that route speech through a large language model (LLM) are far more knowledgeable, but the pipeline delay is long enough to make conversation feel stilted and robotic. Researchers at Sakana AI, the Tokyo-based AI lab […]

Ver mais

arXiv:2601.09867v1 Announce Type: new Abstract: Passive eavesdropping compromises confidentiality in wireless networks, especially in resource-constrained environments where heavyweight cryptography is impractical. Physical layer security (PLS) exploits channel randomness and spatial selectivity to confine information to an intended receiver with modest overhead. However, typical PLS techniques, such as using beamforming, artificial noise, and reconfigurable intelligent surfaces, often involve added active power or specialized deployment, and, in many designs, rely on precise time synchronization and perfect CSI estimation, which limits […]

Ver mais

arXiv:2602.05075v1 Announce Type: new Abstract: As the orbital environment around Earth becomes increasingly crowded with debris, active debris removal (ADR) missions face significant challenges in ensuring safe operations while minimizing the risk of in-orbit collisions. This study presents a reinforcement learning (RL) based framework to enhance adaptive collision avoidance in ADR missions, specifically for multi-debris removal using small satellites. Small satellites are increasingly adopted due to their flexibility, cost effectiveness, and maneuverability, making them well suited for dynamic […]

Ver mais

arXiv:2602.11162v1 Announce Type: new Abstract: Recent studies have identified “retrieval heads” in Large Language Models (LLMs) responsible for extracting information from input contexts. However, prior works largely rely on static statistics aggregated across datasets, identifying heads that perform retrieval on average. This perspective overlooks the fine-grained temporal dynamics of autoregressive generation. In this paper, we investigate retrieval heads from a dynamic perspective. Through extensive analysis, we establish three core claims: (1) Dynamism: Retrieval heads vary dynamically across timesteps; […]

Ver mais

arXiv:2604.06183v1 Announce Type: new Abstract: Responsiveness in large language model (LLM) applications is widely assumed to be critical, yet the impact of latency on user behavior and perception of output quality has not been systematically explored. We report a controlled experiment varying time-to-first-token latency (2, 9, 20 seconds) across two taxonomy-driven knowledge task types (Creation and Advice). Log analyses reveal that user interaction behaviors were robust to latency, yet varied by task type: Creation tasks elicited more frequent […]

Ver mais

arXiv:2603.08755v1 Announce Type: new Abstract: We present textbf{Turn}, a compiled, actor-based programming language — statically typed for schema inference, dynamically typed at the value level — for agentic software: programs that reason and act autonomously by delegating inference to large language models (LLMs). Existing approaches augment general-purpose languages with frameworks, encoding critical invariants (bounded context, typed inference output, credential isolation, durable state) as application-level conventions rather than language guarantees. Turn introduces five language-level constructs that address this gap. […]

Ver mais