What can you do to Microsoft 365 with PowerShell? Turns out - almost anything! Richard talks to Tony Redmond about his ongoing efforts to educate sysadmins about the vast array of capabilities in M365, including all the PowerShell cmdlets that can let you retrieve and control everything in M365. There's now so much information that Tony and his team have created a separate book explicitly focused on automating M365 with PowerShell. The conversation also turns to the role of Copilot - GitHub Copilot- in helping you write better PowerShell and the challenges around M365 Copilot. The goal is to take advantage of the Microsoft Graph - all that information about your M365 Tenant and what is happening inside it.

Links

• Office 365 for IT Pros
• Practical 365 Blog
• Automating Microsoft 365 with PowerShell
• Microsoft Graph SDK
• Copilot for Microsoft 365
• Microsoft Entra PowerShell
• GitHub Copilot
• Overview of Microsoft Graph

Recorded August 8, 2024

How is generative AI evolving, and what can we do about it? While at NDC in Oslo, Richard chatted with Alison Cossette about her work as a data scientist before the ChatGPT explosion in November 2022 and what life has been like since the LLM came to town. Alison talks about the rigor of building AI models using generative AI before ChatGPT and how many of those efforts have diminished when confronted with a friendly, confident language model. Eventually, this rigor will be needed - as the dangers of not managing language models cause problems, and the need for rigor will re-appear. Alison describes steps you can take today to understand how the LLMs you are using are trained and how they are tested. Generative AI is evolving, and you can be part of making it better!

Links

• GitHub Copilot
• Fairly Trained

Recorded June 12, 2024

Leadership wants to get on the AI bandwagon - what are the security risks? While at the Kansas City Developers Conference, Richard sat down with Steve Poole to talk about his experiences helping companies manage the risk of bringing AI into the company. Steve talks about the impact of introducing a new development stack, especially open-source stacks where you aren't sure of the providence of the code - sometimes there's malware in there! The conversation also moves to the various sources of language models and the potential risks. There's an urgency to move quickly on this technology, but don't allow that urgency to shortcut the safety your company will need - you can do this properly!

Links

• Hugging Face

Recorded June 27, 2024