January 2026

The uncomfortable truth: “model choice” is half your prompt engineering If your prompt is a recipe, the model is your kitchen. A great recipe doesn’t help if: the oven is tiny (context window), the ingredients are expensive (token price), the chef is slow (latency), or your tools don’t fit (function calling / JSON / SDK / ecosystem). So here’s a practical comparison you can actually use. Note on “parameters”: for many frontier models, parameter counts are not publicly […]

Ver mais

We study the problem of learning a single neuron under standard squared loss in the presence of arbitrary label noise and group-level distributional shifts, for a broad family of covariate distributions. Our goal is to identify a ”best-fit” neuron parameterized by $mathbf{w}_*$ that performs well under the most challenging reweighting of the groups. Specifically, we address a Group Distributionally Robust Optimization problem: given sample access to $K$ distinct distributions $mathcal p_{[1]},dots,mathcal p_{[K]}$, we seek to approximate $mathbf{w}_*$ that […]

Ver mais

We present a new operator theoretic framework for analysis of complex systems with intrinsic subdivisions into components, taking the form of "residuals" in general, and "telescoping energy residuals" in particular. We prove new results which yield admissibility/effectiveness, and new a priori bounds on energy residuals. Applications include infinite-dimensional Kaczmarz theory for $λ_{n}$-relaxed variants, and $λ_{n}$-effectiveness. And we give applications of our framework to generalized machine learning algorithms, greedy Kernel Principal Component Analysis (KPCA), proving explicit convergence results, residual […]

Ver mais

We present a method for implementing an optical neural network using only linear optical resources, namely field displacement and interferometry applied to coherent states of light. The nonlinearity required for learning in a neural network is realized via an encoding of the input into phase shifts allowing for far more straightforward experimental implementation compared to previous proposals for, and demonstrations of, $textit{in situ}$ inference. Beyond $textit{in situ}$ inference, the method enables $textit{in situ}$ training by utilizing established techniques […]

Ver mais

In the first part of this series, here, I feature a click fraud case that we are working on, litigated by one of the largest law firms in the US.  The input data comes from an Excel repository, automatically processed by an AI agent part of our BondingAI enterprise solutions. It comes with insights generation via automated SQL queries and pattern detection. In other contexts, the data may come from a PDF repository, the Internet, databases, or a […]

Ver mais

Dielectric materials are critical building blocks for modern electronics such as sensors, actuators, and transistors. With the rapid recent advance in soft and stretchable electronics for emerging human- and robot-interfacing applications, there is a surging need for high-performance dielectric elastomers. However, it remains a grand challenge to develop soft elastomers that simultaneously possess high dielectric constants (k, related to energy storage capacity) and low Young’s moduli (E, related to mechanical flexibility). While some new elastomer designs have been […]

Ver mais

There is a dirty secret in product management. Most features that get shipped do nothing. Absolutely nothing. These features might sound great, sound fancy, and get a lot of praise internally. But when it comes to impacting the business, they do F all. They do nothing, not because they aren’t designed well, but because they don’t drive your business model in any meaningful way. The only way to impact your business is to have sustained focus on the […]

Ver mais