Tool: GitHub Repo Stats One of the things I always look for when evaluating a new GitHub repository is the number of commits it has… but that number isn’t visible on GitHub’s mobile site layout. I built this tool to fix that, using this prompt: Given a GitHub repo URL or foo/bar repo ID show information about that repo absorbed via wither REST or graphql CORS fetch() including the number of commits in the repo and other useful […]
La noticia de que Meta va a instalar en los ordenadores de sus empleados estadounidenses una herramienta capaz de registrar movimientos de ratón, clics, pulsaciones de teclado y capturas ocasionales de pantalla para entrenar sus modelos de inteligencia artificial no es simplemente una anécdota más sobre la obsesión de Mark Zuckerberg con la inteligencia artificial. Es, más bien, una magnífica radiografía del momento en que nos encontramos: la empresa ya no solo quiere medir lo que hacen sus […]
When we hear about automation and artificial intelligence replacing jobs, it may seem like a tsunami of technology is going to wipe out workers broadly, in the name of greater efficiency. But a study co-authored by an MIT economist shows markedly different dynamics in the U.S. since 1980. Rather than implement automation in pursuit of maximal productivity, firms have often used automation to replace employees who specifically receive a “wage premium,” earning higher salaries than other comparable workers. […]
arXiv:2605.04269v1 Announce Type: new Abstract: We provide a theoretical analysis of Adam under non-stationary stochastic objectives, separating two regimes: Euclidean tracking under adaptive strong monotonicity of the Adam-preconditioned mean-gradient operator, and high-probability projected stationarity guarantees under general $L$-smooth objectives. In the tracking regime, we derive finite-time expected and high-probability bounds that decompose sharply into four components: initialization, objective drift, a first-moment tracking error governed by $beta_1$, and a preconditioner perturbation governed by $beta_2$. We characterize the burn-in time […]
arXiv:2605.04051v1 Announce Type: new Abstract: In complex real-world settings, optimization is challenged by the presence of diverse models of differing fidelity. In many optimization problems, a single model is treated as the most accurate representation of the underlying system, while other models are evaluated primarily by their agreement with this presumed most accurate model. Yet in real-world applications, model accuracy is rarely known a priori and assuming a single most accurate model can be misleading. This paper addresses […]
arXiv:2605.04051v1 Announce Type: new Abstract: In complex real-world settings, optimization is challenged by the presence of diverse models of differing fidelity. In many optimization problems, a single model is treated as the most accurate representation of the underlying system, while other models are evaluated primarily by their agreement with this presumed most accurate model. Yet in real-world applications, model accuracy is rarely known a priori and assuming a single most accurate model can be misleading. This paper addresses […]
arXiv:2605.04056v1 Announce Type: new Abstract: Representation learning seeks meaningful sensory representations without supervision and can model aspects of human development. Although many neural networks empirically learn useful features, a principled account of what makes a representation “good” remains elusive. We study unsupervised categorization of transformations between pairs of inputs under algebraic constraints. Classical disentanglement favors mutually independent factors and fails when factors are coupled. Our prior Galois-theoretic approach decomposes a group via normal subgroups by learning a product […]
arXiv:2605.04055v1 Announce Type: new Abstract: Adaptive optimizers like AdamW apply uniform hyperparameters across all parameter groups, ignoring heterogeneous optimization dynamics across layers and modules. We address this limitation by proposing MetaAdamW – a new optimizer that integrates a self-attention mechanism to dynamically modulate per-group learning rates and weight decay. The modulation factors are produced by a lightweight Transformer encoder that operates on statistical features (gradient norms, momentum norms, correlations) extracted from each parameter group. To train the attention […]
arXiv:2605.04054v1 Announce Type: new Abstract: Achieving endogenous regime switching is crucial for the emergence of autonomous intelligence, yet remains a central challenge for existing machine learning frameworks, where such transitions are typically externally imposed. In this work, we introduce a classification that distinguishes scalar-reducible dynamics, which can be expressed as gradient flows driven by a scalar objective, from scalar-irreducible dynamics that cannot be reduced to such a form. While most existing machine learning systems operate within the scalar-reducible […]
arXiv:2605.04052v1 Announce Type: new Abstract: Low Earth orbit (LEO) satellites increasingly carry compute hardware capable of on-board processing, yet each satellite generates roughly two orders of magnitude more data than it can downlink per orbit. This mismatch forces operators to decide, for every workload, which computation runs on-board and which runs on the ground, how intermediate data crosses the space-ground boundary through narrow contact windows, and how to maintain delivery guarantees over noisy channels. We present Constraint-Aware Execution […]