Iwan E.

An excellent talk about ATAM 1.Architecture vs Design 2.the strategical and Tactcial difference. 3.Architecture performance and scalability. #SoftwareArchitecture

1

🤔Things are moving so fast in the world of #ai. Introducing SLMs ! ⬇️⬇️⬇️⬇️ Small Langauage Models “Tech giants are shifting focus from large language models to more efficient small language models (SLMs), with Apple and Microsoft introducing models with substantially fewer parameters yet comparable, or even superior, performance in benchmarks.” https://lnkd.in/gvre98xD

2

For enterprises, the recall and precision rates for private data will make or break the success of your genAI projects. This is an excellent study. Progress MarkLogic has been combining semantic graphs, vectors, and regular search with patent pending tech to greatly improve the precision and recall rates of private enterprise data as well. We call this solution “agile semantic RAG.”

11

Can we have LLM routers? Unify has created a solution which abstracts the LLM being used - allowing us to use the best of breed. https://unify.ai/ An interesting concept to combine multiple LLMs #llms #genai #generatieveai #capgemini #llm #opensourceai #capgeminiindia #ai #artificialintelligence #software

6

1 commentaar

🚀 Unlocking the Power of Cognitive Architectures in LLMs/GenAI based applications 🧠 In the fast-paced world of large language models (LLMs), companies face a critical decision: 🏗️ build their own cognitive architectures or rely on third-party infrastructure? While platforms like AWS Bedrock 🌐, Databricks 📊, and Mosaic ML 🧩 shine in providing infrastructure architecture, it's crucial not to mix cognitive architecture and infrastructure architecture for LLM/GenAI-based applications. 🔑 Owning your cognitive architecture is the key to success, regardless of whether you're a tech giant or a business-focused company! It empowers you to: • 🎯 Tailor LLMs to your specific domain and use case • 🗄️ Integrate knowledge bases and vector databases for powerful knowledge retrieval • ✨ Implement cutting-edge techniques like Retrieval-Augmented Generation (RAG) • 🌉 Create a seamless API gateway for easy integration and scalability • 🕵️‍♂️ Maintain control for interpretability, debugging, and compliance • 💡 Fuel innovation and experimentation 🌟 Uber, a company known for its business focus on transportation and delivery, showcases the power of cognitive architectures through its GenAI Gateway 🚗. As highlighted in their blog post (https://lnkd.in/eWRP-3ft), Uber has harnessed the GenAI Gateway to leverage LLMs across 60+ use cases, providing seamless access to models from OpenAI, Vertex AI, and their in-house models through a unified interface. This has streamlined integration and management, enabling Uber to drive innovation and efficiency across their organization. 💡 The optimal approach? Strategically leverage third-party infrastructure like AWS Bedrock, Databricks, and Mosaic ML for scalable compute and deployment while maintaining ownership of your cognitive architecture, knowledge bases, and vector databases. By doing so, you can swiftly innovate and build highly successful products in the fast-paced world of natural language AI. ❓ What are your thoughts on the significance of cognitive architectures in LLMs for companies across various industries, and how do they differ from infrastructure architectures? Share your insights in the comments below! 💬 #CognitiveArchitectures #InfrastructureArchitectures #LLMs #GenAI #AI #NLP #Innovation #Uber #GenAIGateway #AWSBedrock #Databricks #MosaicML #BusinessTransformation #Gonnect

3

The swift and widespread adoption of Generative AI has permeated business sectors worldwide. With transcription tools and content creation readily available, AI's potential to reshape the future is endless. From software tools that AI will render obsolete to new ways of coding, it poses profound challenges for software development and the industry. #dev #software #product #ai #genai #vode #tools Read more about traceability in AI-enhanced code and a developer's guide here: [Link to the article](https://lnkd.in/gryNjWra)

1

2 commentaren

AI Ramblings AI Musings Have you ever wondered about the reliability of large language models? Cleanlab, a dynamic AI startup originating from MIT's quantum computing lab, introduces an innovative solution - the Trustworthy Language Model. LLM's are renowned for their creative abilities but have often raised concerns about accuracy. With the introduction of the "Trustworthy Language Model", users can gauge the reliability of generated outputs on a scale from 0 to 1. The tool should empower users and businesses to make informed decisions, distinguishing between trustworthy responses and those that may not be accurate. In essence, it's like having a BS-o-meter for your chatbot! "Addendum: it's worth noting that the example in the story is from GPT3.5 and that GPT4 is much better, although still nowhere near perfect!" #AI #TrustworthyAI #Innovation #artificialintelligence #aimusings #airamblings #cleanlab

1

2 commentaren

Ready to get started with AI orchestration for your application resources? We wrote this article to show how to connect your repositories and submit prompts to auto-generate templates you can use to launch your environments on-demand. #platformengineering #infrastructureascode #devops

12

AI projects remain work in progress, pilots, say CxOs https://buff.ly/4eBbwvy Do-it-yourself AI projects are alive and well as CxOs are trying multiple approaches for genAI, getting some projects to production and looking for better returns #AIF24NYC

1

Diagram of Thought (DoT): An AI Framework that Models Iterative Reasoning in Large Language Models (LLMs) as the Construction of a Directed Acyclic Graph (DAG) within a Single Model https://flip.it/Mh_Mhu

1

AIOS - Architecture of Interoperable Information Systems (now available for free download)   📚 In 2010, I submitted my doctoral thesis, introducing the Architecture of Interoperable Information Systems (AIOS), a reference architecture for digitalizing large interoperable enterprise systems. Topic: If enterprises want to engage in cross-organizational business process automation, e.g. in B2B-scenarios, the involved digital systems must be able to work together, i.e. they need to be interoperable. The question is, how to achieve this? How does a sustainable, efficient, and secure design of these complex digital ecosystems look like? And, for creating this landscape, which layers must be addressed, in which sequence?    💻 These were the heydays of #ModelDrivenArchitcture, #ServiceOrientedArchitecture (SOA) and the #WebServiceStack. The latter contained sophisticated XML-based standards, describing for example service contracts (WSDL), business objects (XSD), business processes (BPEL Frank Leymann Jan Mendling), and roles and rights (XACML). Here also elegant concepts were developed for decoupling and correlating internal process elements ("private processes") and their adjacent public process elements ("public processes") visible in a collaboration, alongside a comprehensive view that integrates complementary public processes ("global processes"). 🏛 Complementary, the "Architecture of Integrated Information Systems" (ARIS), introduced by August-Wilhelm Scheer outlined the foundational pillars for the architecture of large digital enterprise systems from a business perspective: Business functions, business objects ("data view"), business processes, and roles and rights ("organization view"). According to ARIS (and similar to #MDA), these views needed to be addressed on three levels: business design, technical design, and implementation. 🚀 AIOS integrates the core concepts from Service-oriented Architecture, MDA, Collaborative Business, and ARIS. It serves as a generic blueprint for large organizations to develop interoperable information systems by systematically adjusting and extending their internal information systems. AIOS is product- and vendor-independent, providing a generic framework for the layers, views, relationships, and technical means necessary to establish interoperable information systems efficiently. 🙏 AIOS drew on the findings of various research projects from the #EuropeanUnion on #interoperability, e.g. #ATHENA, #R4eGov, and #Interop. Fun days with great colleagues, e.g. Christine Legner Kristin Weber Ulrike G. Thomas Knothe Maria Wimmer. Now, the Logos publishing house has generously made AIOS available for free download; please find the link in the comments section below.   #Interoperability #EnterpriseArchitecture #enterpriseDigitalization #processAutomation #dataContracts #EAMfundamentals #AIOS #ARIS

39

2 commentaren

Strong data foundation is fundamental to AI strategy. A timely and refreshing conversation with Andrew Churchill where we focus on the data objectives and not GenAI ! #backtobasics

16

Cybersecurity at a crossroads: Time to shift to an architectural approach https://lnkd.in/gp8tR-fi #cybersecurity #connectivity #automation #intelligence #scale #cloud #growth #GenerativeAl #digitalsecurity #architectural #analytics #operations

3