Armchair Architects: The Danger Zone (Part 1)

In this two-part episode of the #AzureEnablementShow, David talks to our #ArmchairArchitects-Uli and Eric (@mougue )- about the ethical and responsible considerations for architects should consider when using large language models (LLMs) in their applications, including the risks of leaking confidential information, societal biases, and increasing regulations.
Resources
• Confidential AI learn.microsoft.com/azure/con...
• Responsible and trusted AI learn.microsoft.com/azure/clo...
• Azure confidential computing partners learn.microsoft.comazure/conf...
• Confidential Computing on Azure learn.microsoft.com/azure/con...
• Blog: Considerations for Ethical and Responsible Use of AI in Applications techcommunity.microsoft.com/t...
Related Episodes
• Armchair Architects: The Danger Zone (Part 2) aka.ms/azenable/147
• Watch more episodes in the Armchair Architects Series aka.ms/azenable/ArmchairArchi...
• Watch more episodes in the Well-Architected Series aka.ms/azenable/yt/wa-playlist
• Check out the Azure Enablement Show aka.ms/AzureEnablementShow
Chapters
0:00 Introduction
0:53 Thinking about Confidentiality
1:22 AI and ML vs. LLMS
2:14 Transparency in algorithms
2:35 Explainable AI
4:16 Picking a model and partner
6:48 Explainability or Observability
7:48 Create model using JSON
9:50 To be continued …