I keep hearing the same question at every engineering offsite, Slack thread, and investor pitch: “What’s the best model right now — GPT, Claude, or Gemini?” I spent the last several months building and debugging agent-based systems, and I think this is the wrong question entirely. The evidence is now overwhelming: what determines whether an AI agent succeeds in production is not the model underneath it, but the infrastructure wrapped around it. I am going to lay out my hypothesis, test […]

Ver mais

Large language models (LLMs) have transformed how we interact with AI, but one size doesn’t fit at all. Out-of-the-box LLMs are trained with broad, general knowledge and improved for a wide range of use cases, but they often fall short when it comes to domain-specific tasks, proprietary workflows, or unique business requirements. Enterprise customers increasingly need specialized LLMs that deeply understand their proprietary data, business processes, and domain-specific terminology. Without customization, you’re forced to choose between accepting generic […]

Ver mais

Allegro is a machine learning interatomic potential (MLIP) model designed to predict atomic properties in molecules using E(3) equivariant neural networks. When training this model, there tends to be a trade-off between accuracy and inference time. For this reason we apply multi-objective hyperparameter optimization to the two objectives. Additionally, we experiment with modified architectures by making variants of Allegro some by adding strictly classical multi-layer perceptron (MLP) layers and some by adding quantum-classical hybrid layers. We compare the […]

Ver mais

arXiv:2601.16407v1 Announce Type: new Abstract: Large language models (LLMs) make next-token predictions based on clues present in their context, such as semantic descriptions and in-context examples. Yet, elucidating which prior tokens most strongly influence a given prediction remains challenging due to the proliferation of layers and attention heads in modern architectures. We propose Jacobian Scopes, a suite of gradient-based, token-level causal attribution methods for interpreting LLM predictions. By analyzing the linearized relations of final hidden state with respect […]

Ver mais

OpenAI engineers used large-scale core dump analysis to debug rare infrastructure crashes, uncovering both a hardware fault and a long-standing software bug.

Ver mais

Machine learning techniques are now routinely encountered in research laboratories across the globe. Impressive progress has been made through ML and AI techniques with regards to large data set processing. This progress has increased the ability of the experimenter to digest data and make novel predictions regarding phenomena of interest. However, machine learning predictors generated from data sets taken from the natural sciences are often treated as black boxes which are used broadly and generally without detailed consideration […]

Ver mais

arXiv:2602.12338v1 Announce Type: new Abstract: Token Communications (TokenCom) has recently emerged as an effective new paradigm, where tokens are the unified units of multimodal communications and computations, enabling efficient digital semantic- and goal-oriented communications in future wireless networks. To establish a shared semantic latent space, the transmitters/receivers in TokenCom need to agree on an identical tokenizer model and codebook. To this end, an initial Tokenizer Agreement (TA) process is carried out in each communication episode, where the transmitter/receiver […]

Ver mais

I spent years calling models via API : Bedrock, Sagemaker, Anthropic. This week was about understanding what’s actually happening inside the box, and why that matters for building systems around it. Coming into this project, I had built production AI systems on AWS Bedrock using flows, agents. I knew how to wire models into applications. What I didn’t know was what the models were actually doing with the text I gave them, why RAG works at all, or […]

Ver mais

We propose a hierarchical entity-centric framework for offline Goal-Conditioned Reinforcement Learning (GCRL) that combines subgoal decomposition with factored structure to solve long-horizon tasks in domains with multiple entities. Achieving long-horizon goals in complex environments remains a core challenge in Reinforcement Learning (RL). Domains with multiple entities are particularly difficult due to their combinatorial complexity. GCRL facilitates generalization across goals and the use of subgoal structure, but struggles with high-dimensional observations and combinatorial state-spaces, especially under sparse reward. We […]

Ver mais