Subscribe • Previous Issues Enhancing AI Retrieval Systems with Structured Data I’ve previously written about GraphRAG, a form of Retrieval-Augmented Generation (RAG) that combines the power of vector embeddings with knowledge graphs (KG). While traditional RAG relies solely on vector-based similarity searches to retrieve relevant information, GraphRAG introduces knowledge graphs to represent and traverse relationships between entities,Continue reading “Structure Is All You Need”
Author Archives: Ben Lorica
Addressing Context Loss in RAG Systems with Contextual Retrieval
Context loss is a known challenge faced by traditional Retrieval-Augmented Generation (RAG) systems, stemming from the necessary practice of splitting large documents into smaller chunks for efficient processing. When documents are divided, individual chunks often lack sufficient contextual information, making it difficult for the retrieval system to identify and utilize relevant information effectively. For example,Continue reading “Addressing Context Loss in RAG Systems with Contextual Retrieval”
How Tech-Forward Organizations Build Custom AI Platforms: A Feature Breakdown
In my previous article, “Why Digital-First Companies Are Building Their Own AI Platforms”, I explored why many tech-forward companies are opting to build their own AI platforms rather than relying on off-the-shelf solutions. The piece sparked considerable interest, with readers eager to explore the specifics of these custom platforms. A common reaction was: now thatContinue reading “How Tech-Forward Organizations Build Custom AI Platforms: A Feature Breakdown”
Custom AI Platforms: The Features Driving Innovation
Subscribe • Previous Issues How Tech-Forward Organizations Build Custom AI Platforms: A Feature Breakdown In my previous article, “Why Digital-First Companies Are Building Their Own AI Platforms”, I explored why many tech-forward companies are opting to build their own AI platforms rather than relying on off-the-shelf solutions. The piece sparked considerable interest, with readers eager to exploreContinue reading “Custom AI Platforms: The Features Driving Innovation”
Ray Summit 2024: Advancing AI Platforms and Applications
In a previous article, I explored why many leading companies are building custom AI platforms, even when a range of off-the-shelf options exists. The reasons vary from seeking greater adaptability to establishing market differentiation through tailored AI capabilities. As more businesses push toward these bespoke platforms, scaling becomes a central challenge. Few technologies match theContinue reading “Ray Summit 2024: Advancing AI Platforms and Applications”
The Future of Analysts: Orchestrating AI for Strategic Insights
I’ve written a couple of posts examining the significant challenges confronting startups in the AI landscape, particularly those involved in training foundation models like Large Language Models (LLMs). In one post, I highlighted Meta’s release of the world’s largest “open weights” foundation model—a notable development in an environment where OpenAI, another major player, is grapplingContinue reading “The Future of Analysts: Orchestrating AI for Strategic Insights”
Rethinking Analyst Roles in the Age of Generative AI
Subscribe • Previous Issues The Future of Analysts: Orchestrating AI for Strategic Insights I’ve written a couple of posts examining the significant challenges confronting startups in the AI landscape, particularly those involved in training foundation models like Large Language Models (LLMs). In one post, I highlighted Meta’s release of the world’s largest “open weights” foundation model—a notableContinue reading “Rethinking Analyst Roles in the Age of Generative AI”
The Case Against SB 1047
California SB 1047 (California Safe and Secure Innovation for Frontier Artificial Intelligence Models Act) is a proposed California state bill that aims to regulate the development and deployment of large, advanced AI models by imposing safety and testing requirements on developers. The bill is now in the hands of Governor Gavin Newsom, who will eitherContinue reading “The Case Against SB 1047”
Pipe SQL: Google’s Answer to SQL’s Limitations
As a long-time SQL user, I still turn to it whenever I need to work with tabular data, preferring it over dataframe libraries like Pandas. SQL’s syntax is easier to recall and aligns well with set theory concepts, making it intuitive for those familiar with basic mathematical logic. The presence of an optimizer further enhancesContinue reading “Pipe SQL: Google’s Answer to SQL’s Limitations”
Cerebras Inference: First Impressions
As someone who has closely followed the AI hardware landscape for years, I’ve long been particularly bullish on Cerebras among the startups building specialized AI chips. Their founding team, composed of chip industry veterans with a proven track record of delivering cutting-edge hardware, has consistently impressed me. I’ve had the pleasure of seeing them keynoteContinue reading “Cerebras Inference: First Impressions”