Any solution to the mythical problem in question has remained elusive for centuries. It is deemed more difficult than proving the Riemann Hypothesis, yet its formulation can be understood by kids in elementary school. The question is whether or not the digits of mathematical constants such as π, behave like a random sequence. This article ..read more

Here I explain how we manage to avoid hallucinations with our home-made Enterprise RAG/LLM. The most recent article on the topic is available here. We do it with no training and zero parameter. By zero parameter, I mean no neural network parameters — the typical 40B you see in many LLMs, that stands for 40 ..read more

In my most recent articles and books, I discussed our radically different approach to building enterprise LLMs from scratch, without training, hallucinations, prompt engineering or GPU, while delivering higher accuracy at a much lower cost, safely, at scale and at lightning speed (in-memory). It is also far easier to adapt to specific corpuses and business ..read more

This article started as a curious question: how much taller a skyscraper needs to be in order to be perceived as twice its actual height? I assumed that the observer was at ground level at a horizontal distance d from the building, and that the real height is H.  We all know that the building […] The post How the Brain Estimates Distances, Heights and Velocities, with Computer Vision Applications first appeared on Machine Learning Techniques ..read more

In this article, I discuss LLM 1.0 (OpenAI, Perplexity, Gemini, Mistral, Claude, Llama, and the likes), the story behind LLM 2.0, why it is becoming the new standard architecture, and how it delivers better value at a much lower cost, especially for enterprise customers. 1. A bit of history: LLM 1.0 LLMs have their origins […] The post From 10 Terabytes to Zero Parameter: The LLM 2.0 Revolution first appeared on Machine Learning Techniques ..read more

I get many questions about the radically different LLM technology that I started to develop 2 years ago. Initially designed to retrieve information that I could no longer find on the Internet, not with search, OpenAI, Gemini, Perplexity or any other platform, it evolved to become the ideal solution for professional enterprise users. Now agentic […] The post LLM 2.0, the New Generation of Large Language Models first appeared on Machine Learning Techniques ..read more

The technology described here boosts exhaustivity and structuredness in LLM prompt results, efficiently exploiting the knowledge graph and contextual structure present in any professional or enterprise corpus. The case study deals with public financial reports from Nvidia, available as PDF documents. In this article, I discuss the preprocessing steps used to turn a PDF repository […] The post LLM Deep Contextual Retrieval and Multi-Index Chunking: Nvidia PDFs, Case Study first appeared on Machine Learning Techniques ..read more

Have you tried the xLLM web API? It allows you to fine-tune and debug an agentic multi-LLM in real time. The input data is part of the anonymized corporate corpus of a Fortune 100 company, dealing with AI policies, documentation, integration, best practices, references, onboarding, and so on. It features one sub-LLM. The full corpus […] The post No-Code LLM Fine-Tuning and Debugging in Real Time: Case Study first appeared on Machine Learning Techniques ..read more

In this article, you will find my PowerPoint presentation describing the most recent features of xLLM, a CPU-based, full context, secure multi-LLM with real-time fine-tuning & explainable AI. It includes several new diagrams describing the innovative architecture, upcoming developments, new features and different use cases. Content Enterprise use case: corporate corpus of a Fortune 100 […] The post xLLM: New Generation of Large Language Models for Enterprise first appeared on Machine Learning Techniques ..read more

In this short paper, I discuss two topics. First, strategies to trade the S&P 500 index with few trades over long time periods, offering best exit, entry and re-entry points during the journey, to beat the baseline return. The baseline consists of staying long the whole time. The dataset has 40 years’ worth of daily […] The post Visualizing Trading Strategies that Consistently Outperform the Stock Market first appeared on Machine Learning Techniques ..read more