Tag: AI and Machine Learning

Navigating the world of generative AI can feel like exploring uncharted waters, especially when it comes to bringing a model into production. This blog dives into the crucial steps of selecting the right Large Language Model (LLM) for your specific needs, drawing insights from a recent AWS conference. From understanding the nuances of each model to leveraging an AI Gateway for a smoother deployment, this guide offers practical advice to ensure your generative AI application is both robust and future-proof.

Hear from our experience design expert Anthony Vermeulen to learn how building real-world solutions with generative AI is a journey of discovery and adaptation. While there’s plenty of information on using generative AI tools, there’s less on designing for generative AI experiences. After wrapping up a project focused on increasing internal productivity through generative AI proof of concepts, Anthony shares key learnings and guidance for designers venturing into this innovative space.

Explore how to harness the best of traditional machine learning by generating synthetic data with LLMs for training compact, efficient ML models. To illustrate this, I ran an experiment using GPT-4o to generate synthetic data for three text classification tasks: spam detection, product classification, and sentiment analysis. I’ve also set out some recommendations for anyone looking to leverage synthetic data generated by LLMs for training efficient ML models.

Recently, DiUS encountered a flurry of questions about multilingual chatbots from two clients in different industries. A healthcare provider needed to communicate with diverse, non-English speaking patients, while a travel company sought to enhance experiences for non-English speaking visitors. Both scenarios highlighted a common need: breaking down language barriers to improve user experience. Multilingual chatbots powered by generative AI offer a promising solution for seamless global communication.