How to choose a LLM partner for your AI project

Post Content

What are the processes and criteria you should consider when choosing a large language model (LLM) or a foundational model (FM) for your AI project, and are the trade-offs between building your own model or using a hosted service? What are some of the challenges of trusting and validating the outputs of LLMs and FMs? When choosing an LLM partner, what things should you think about?

Uli, Eric (@mougue), and David—AKA the #ArmchairArchitects—provide the answers to these questions and much, much more on this episode of the #AzureEnablementShow.

Resources
• How to deploy large language models with Azure AI Studio https://learn.microsoft.com/azure/ai-studio/how-to/deploy-models-open
• Explore the model catalog in Azure AI Studio https://learn.microsoft.com/azure/ai-studio/how-to/model-catalog
• Training: Create a large language model deployment https://learn.microsoft.com/training/modules/large-language-model-deployment
• Get Certified: Azure AI Fundamentals https://learn.microsoft.com/credentials/certifications/azure-ai-fundamentals

Related Episodes
• Armchair Architects: Danger! Confidentiality and Ethics (part 1) https://aka.ms/azenable/146
• Armchair Architects: Danger! Confidentiality and Ethics (part2) https://aka.ms/azenable/147
• Armchair Architects: Are AI Charters Valuable? https://aka.ms/azenable/148
• Watch more episodes in the Armchair Architects Series https://aka.ms/azenable/ArmchairArchitects
• Watch more episodes in the Well-Architected Series https://aka.ms/azenable/yt/wa-playlist
• Check out the Azure Enablement Show https://aka.ms/AzureEnablementShow

Chapters
0:00 Introduction
0:58 A variety of models
2:18 Build your own?
4:20 ROI vs. innovation
5:10 Partner criteria
6:04 Open-source considerations
6:15 Different service offerings
6:53 Business decisions
7:10 Review the Partner’s Charter
8:08 Charters aren’t just for AI
9:06 Consider AI as you would other business decisions
10:45 LLMs are big and hard to understand
10:54 You must be able to trust your LLM
13:34 A final word Read More Microsoft Developer