Composo

This week, our founding team had the opportunity to be part of EWOR’s community house in Sweden! Beyond the amazing Gothenburg backdrop, we deep-dived into product development and had productive exchanges with other EWOR Fellows and their exciting startups. Thank you, Daniel W. Dippold & EWOR for this opportunity to learn, connect, and grow. #Composo #EWOR #CommunityHouse

💾😱 using the chatgpt research preview today is like buying a server and hosting a html webpage in 1992 👇 📱apps, IM and social media only became possible because of the boom in the mid to late 90s which brought javascript, server-side programming, cookies, and more recently web frameworks, design tools and mobile networks LLMs are the core technology, but it will take years to create the ecosystem application developers need to build the killer app what do you think are the first fundamental technologies to emerge? model triage and tool usage perhaps? 🤔 #AI #chatgpt #llm #promptengineering [Qin 2023 2304.08354]

Arcus's 'RAG at planet scale' approach - using a multi-tiered retrieval at increasing levels of granularity enables LLMs to better incorporate accurate context, and to do so at a huge scale! https://lnkd.in/ewm42Kd9 #artificialintelligence #generatieveai

Are you ready to take a deep dive into the world of language model evaluation? 🌊 Let's explore the four crucial elements together and revolutionize the way we assess AI performance! 🚀 1️⃣ What to change: Imagine your language model as a musical instrument. To enhance its performance, you have the power to tweak the model, prompt, temperature, and even the architecture. It's like fine-tuning an instrument to play the perfect melody that resonates with your goals. 2️⃣ What quality to measure: Core intelligence takes the center stage, encompassing accuracy, logic/reasoning & knowledge. In addition, softer skills of natural language quality as well safety, reliability & operational performance are critical. It's like evaluating the harmonious blend of art and science, ensuring that your language model not only provides accurate answers but also does so with style and grace. 💫 3️⃣ How to measure: Conducting the symphony of evaluation requires a range of tools. From manual evaluation to automatic comparison with ideal responses, to harnessing the power of policy or classifier models: you have an array of instruments at your disposal. It's like conducting a symphony, with each instrument playing its part to create a harmonious evaluation process. 4️⃣ Varied Test Cases: Effective evaluation demands a spectrum of test cases that mimic real-world scenarios. These cases can range from manual human queries to adversarial testing and even simulations of user interactions. The goal is to cover a diverse landscape of potential interactions, mirroring the complexity and richness of the language model's application environment. This diversity in test cases allows for a more robust assessment of the model's performance in practical settings. 🌱 Here at Composo, we believe that LLM model evaluation should be an accessible and empowering process. We’re building a platform that offers a suite of advanced features designed to revolutionize the way you evaluate language model applications. Join us in shaping the future of performance testing! 🔥🚀 Read more at https://lnkd.in/eg8_8UYs ✨ How do you approach language model evaluation? Share your experiences and let's shape the future of performance testing together! 💬🌟 #AI #LanguageModels #PerformanceTesting