Category: GenAI
-
Could Multi-Billion Token Prompts Make Retrieval-Augmentation Obsolete?
The ability for large language models to understand and generate relevant responses hinges on the amount of context they can process at once—the “prompt window” size. For current models like GPT-4, this is limited to around 8,000 tokens. To compensate, techniques like Retrieval-Augmented Generation (RAG) have been developed. RAG models first retrieve relevant documents or…
-
What is LOrA?
When it comes to Gen AI, efficiency and adaptability are key. Low-Rank Adaptation (LOrA), is enabling more optimized AI operation. What is LOrA?LOrA is a technique that allows us to adapt pre-trained AI models to new tasks or datasets without the need for extensive retraining. Instead of updating all parameters in a model, LOrA focuses…
-
There are Security Risks with Gen AI but You can Control Them
As a leader, you can’t help but feel intrigued or maybe compelled by the concept that you most likely hear many times a day, generative AI. This technology is like a magic wand that can automate mundane tasks, spark creative genius, and supercharge productivity across your organization. But you’re also a level headed person. You…
-
Why you should learn prompt engineering now, even if it will not be needed in the future …
Forrester predicted, a whopping 60% of employees will be trained in prompt engineering by 2024! (Forrester) But what exactly is prompt engineering, and why is it the skill everyone will soon be scrambling to master? Prompt engineering is the craft of designing queries that steer Generative AI models like ChatGPT and Claude to deliver highly…
-
The Rising Value of Vector Indexes for Generative AI
As Gen AI solutions begin to become a common component of data ecosystems, one approach that’s quickly becoming a foundational feature is Retrieval-Augmented Generation (RAG), which combines the power of large language models with external knowledge retrieval. RAG systems work by first retrieving relevant information from a knowledge base (e.g., Wikipedia, corporate documents) and then…
-
Data Clean Rooms for Generative AI
Could Data Clean Rooms open new collaborative opportunities with GenAI? This security-centric technology could potentially unlock new use cases. 𝗪𝗵𝗮𝘁 𝗶𝘀 𝗮 𝗗𝗮𝘁𝗮 𝗖𝗹𝗲𝗮𝗻 𝗥𝗼𝗼𝗺? A data clean room is a secure environment where different organizations can share and analyze data sets while maintaining strict controls around data privacy and security. The data clean room…
-
Digital Twins … Use of Gen AI for Synthetic Data Creation
Generative AI has been making waves in the tech world, and one of the most promising applications is in the realm of synthetic data creation. But what exactly is synthetic data, and how can generative AI be used to create it? Synthetic data refers to artificial data that is computer-generated to mimic real-world data. This…
-
Fine-tuning Large Language Models
Fine-tuning Large Language Models is like hiring a specialist with exact experience for the best outcomes. Like an arm wrestler, intensely training to be extremely proficient at performing a specific task. That’s essentially what fine-tuning is for large language models (LLMs) – a way to customize a powerful, general-purpose model to specialize in your organization’s…
-
The Rejuvenation of Modern Data Lakes to Support Generative AI
The era of generative AI has ushered in a new wave of innovation and disruption across industries. As these models become more sophisticated and widely adopted, the demand for high-quality, diverse, and well-structured data has skyrocketed. This may have potentially reignited interest in modern data lake architectures, which offer a compelling solution for managing the…
-
Explaining: Explainable AI (XAI)
In the ever-evolving world of technology, Artificial Intelligence (AI) continues to make leaps and bounds, enhancing how we work, make decisions, and interact with the world around us. A pivotal aspect of this transformation is Explainable AI (XAI), which is steering the conversation from mere outcomes to understanding the ‘how’ and ‘why’ behind AI decisions.…