In this episode, Scott Hanselman and Mark Russinovich dive into the technical side of modern AI research and development workflows. They discuss the power of remote development with VS Code, building custom chatbot tools for jailbreak testing, and exploring token probabilities with log probes. Mark also shares how he leveraged AI to generate a working UX in one shot, why temperature settings matter for model outputs, and his plans to open source his custom chatbot client.

Takeaways:

• Discover how Mark uses VS Code split between local and cloud for AI research
• Explore the risks and creativity behind context injection jailbreak
• Get insights into model temperature settings and output logprobs

Who are they?

View Scott Hanselman on LinkedIn

View Mark Russinovich on LinkedIn

Watch Scott and Mark Learn on YouTube

Listen to other episodes at scottandmarklearn.to

Discover and follow other Microsoft podcasts at microsoft.com/podcasts

Hosted on Acast. See acast.com/privacy for more information.

In this episode, Scott Hanselman and Mark Russinovich explore the challenges and opportunities of coding with AI assistants. They compare different models, discuss the quirks of “vibe coding,” and share insights on building tools that bridge LLMs and APIs. Mark walks through his experience developing an academic reference checker, highlighting how AI can help structure messy data, uncover edge cases, and speed up complex development work. The conversation also touches on the evolving joy of coding, from puzzle-solving by hand to managing AI-driven workflows, and how these shifts are reshaping both productivity and creativity.

Takeaways:

• Mark’s journey building an academic reference checker with AI
• How AI assistants are changing the way developers find joy in coding
• RefChecker source code: https://github.com/markrussinovich/refchecker

Who are they?

View Scott Hanselman on LinkedIn

View Mark Russinovich on LinkedIn

Watch Scott and Mark Learn on YouTube

Listen to other episodes at scottandmarklearn.to

Discover and follow other Microsoft podcasts at microsoft.com/podcasts

Hosted on Acast. See acast.com/privacy for more information.

In this episode, Scott Hanselman and Mark Russinovich share strategies for conducting more effective and purposeful one-on-one meetings. They emphasize the value of tailoring the approach to each individual, encouraging agenda-setting in advance, and prioritizing critical topics to ensure they are addressed. The discussion covers best practices for providing and receiving constructive feedback, maintaining visibility across teams, and striking a balance between trust and accountability. They also address the importance of recognizing contributions, differentiating between credit and “lift,” and using one-on-ones to proactively identify and remove obstacles.

Takeaways:

• Tailor meeting style to each person’s preferences for communication and frequency
• Avoid over-preparation or unnecessary large meetings when a small discussion will suffice
• Share discussion topics ahead of one-on-ones with senior leaders to maximize value

Who are they?

View Scott Hanselman on LinkedIn

View Mark Russinovich on LinkedIn

Watch Scott and Mark Learn on YouTube

Listen to other episodes at scottandmarklearn.to

Discover and follow other Microsoft podcasts at microsoft.com/podcasts

Hosted on Acast. See acast.com/privacy for more information.

In this episode of Scott and Mark Learn To, Scott Hanselman and Mark Russinovich explore vibe coding with AI, testing how Copilot Agent Mode can analyze their transcripts to see who talks more on the show. They discuss coding with AI as a collaborative sculpting process, debate crediting AI for its contributions, and reflect on the human judgment still needed for prompting and refining outputs. Along the way, they generate graphs, poke fun at each other’s talk time, and share insights on how AI is changing coding and creative work.

Takeaways:

• See how Copilot Agent Mode can generate graphs from transcripts
• Learn the difference between vibe coding and spec-driven development
• Explore the potential for interactive charts using D3.js for podcast data

Who are they?

View Scott Hanselman on LinkedIn

View Mark Russinovich on LinkedIn

Watch Scott and Mark Learn on YouTube

Listen to other episodes at scottandmarklearn.to

Discover and follow other Microsoft podcasts at microsoft.com/podcasts

Hosted on Acast. See acast.com/privacy for more information.

In this episode of Scott and Mark Learn To, Scott Hanselman and Mark Russinovich discuss innovative tools they built with AI assistance: Mark’s smart directory navigation tool that streamlines moving through nested folders by typing partial names, and Scott’s study website that transforms complex topics into structured, digestible material with AI-generated answers and progress tracking. They explore the challenges of AI “hallucination,” where models invent detailed but fictional information, and share insights on computer science history, including Leslie Lamport’s contributions. Their conversation also touches on evolving UI design trends from minimalist styles to flashy effects like “liquid glass” and debates the balance between aesthetics, usability, and energy efficiency in modern technology.

Takeaways:

• Challenges of owning gaps in knowledge and the value of asking questions boldly
• How AI can invent convincing but false project details
• Mark demonstrates his new AI-assisted directory navigation tool called MCD

Who are they?

View Scott Hanselman on LinkedIn

View Mark Russinovich on LinkedIn

Watch Scott and Mark Learn on YouTube

Listen to other episodes at scottandmarklearn.to

Discover and follow other Microsoft podcasts at microsoft.com/podcasts

Hosted on Acast. See acast.com/privacy for more information.

In this episode of Scott and Mark Learn To, Scott Hanselman and Mark Russinovich Scott shares the behind-the-scenes stress and preparation that went into his recent TEDx talk, which required memorizing a 12-minute script and performing it without a teleprompter. Mark Russinovich opens up about how he experiences stress when his schedule gets out of control, and both hosts discuss the importance of mindfulness, exercise, having work besties, and managing social energy. The episode is packed with practical tips, vulnerable moments, and reflections on what it really takes to perform at a high level, whether it’s on stage, at work, or in life.

Takeaways:

• Trusted colleagues make high-pressure jobs sustainable
• Skill is built through reps, not just raw ability
• Repetition, feedback, and coaching turned Scott’s talk into something powerful

Who are they?

View Scott Hanselman on LinkedIn

View Mark Russinovich on LinkedIn

Watch Scott and Mark Learn on YouTube

Listen to other episodes at scottandmarklearn.to

Discover and follow other Microsoft podcasts at microsoft.com/podcasts

Hosted on Acast. See acast.com/privacy for more information.

In this episode of Scott and Mark Learn To, Scott Hanselman and Mark Russinovich dive deep into the topic of self-promotion, visibility, and personal branding. They explore the blurry lines between promoting your work, representing your company, and building a personal brand—whether intentional or not. With humor, honesty, and vulnerability, they reflect on online criticism, handling stress, and the challenge of staying authentic while being visible.

Takeaways:

• Why personal branding doesn’t always mean having a “strategy”
• How to balance work visibility with personal authenticity
• The challenge of managing side projects and perception within corporate environments

Who are they?

View Scott Hanselman on LinkedIn

View Mark Russinovich on LinkedIn

Watch Scott and Mark Learn on YouTube

Listen to other episodes at scottandmarklearn.to

Discover and follow other Microsoft podcasts at microsoft.com/podcasts

Hosted on Acast. See acast.com/privacy for more information.

In this episode of Scott and Mark Learn To, Scott Hanselman and Mark Russinovich dive into the chaotic world of large language models, hallucinations, and grounded AI. Through hilarious personal stories, they explore the difference between jailbreaks, induced hallucinations, and factual grounding in AI systems. With live prompts and screen shares, they test the limits of AI's reasoning and reflect on the evolving challenges of trust, creativity, and accuracy in today's tools.

Takeaways:

• AI is getting better, but we still need to be careful and double check our work
• AI sometimes gives wrong answers confidently
• Jailbreaks break the rules on purpose, while hallucinations are just AI making stuff up

Who are they?

View Scott Hanselman on LinkedIn

View Mark Russinovich on LinkedIn

Watch Scott and Mark Learn on YouTube

Listen to other episodes at scottandmarklearn.to

Discover and follow other Microsoft podcasts at microsoft.com/podcasts

Hosted on Acast. See acast.com/privacy for more information.