Retrieval augmented generation (RAG) has become the standard in long-context question answering (QA) systems. However, typical implementations of RAG rely on a rather naive retrieval mechanism, in which texts whose embeddings are most similar to that of the query are deemed most relevant. This has consequences in subjective QA tasks, where the most relevant text may not directly contain the answer. In this work, we propose a novel extension to RAG systems, which we call Retrieval from AI Derived Documents (RAIDD). RAIDD leverages the full power of the LLM in the retrieval process by deriving inferred features, such as summaries and example questions, from the documents at ingest. We demonstrate that this approach significantly improves the performance of RAG systems on long-context QA tasks.

Nexar will leverage Veniam's technology at the edge, making data flows efficient, cost effective and easier for different cars to collaborate in understanding the world and thus drive safely Nexar, a leading computer vision company, and the number one consumer smart dash cam seller in the United States, announced today a strategic partnership with Veniam, the leading provider of intelligent networking for the internet of moving things. Using Veniam's software APIs, Nexar will be able to better collect the images it needs to create an AI-digital twin of US roads. This will enable Nexar to make the most of all available wireless networks (4G/5G, Wi-Fi, mesh…) and transfer massive amounts of data to the cloud in a secure and cost-effective way. This cooperation will also help to further expand the wealth of vision data it collected by Nexar, to build a real time twin of the road, improve safety, train Autonomous Vehicles (AVs) and inform city decisions, as well as "see" changes in the road. "Veniam's capabilities are a great fit for Nexar and will help it realize its vision of seeing what's ahead on the road," said Eran Shir, Co-founder and CEO of Nexar.

Why is artificial intelligence, or AI, so much in the news these days? How big an impact will it have on business? What will it mean for jobs? What do ordinary people need to understand? These were some of the questions that motivated a recent salon dinner discussion that Techonomy hosted on AI.