# Scott & Mark Learn To… Chatbot, Another Vibe-Coded Project by Mark

Page: https://stenobird.com/podcast/scott-mark-learn-to-7043872/scott-mark-learn-to-chatbot-another-vibe-coded-project-by-mark
Text version: https://stenobird.com/podcast/scott-mark-learn-to-7043872/scott-mark-learn-to-chatbot-another-vibe-coded-project-by-mark.md
Podcast: [Scott & Mark Learn To...](https://stenobird.com/podcast/scott-mark-learn-to-7043872)
Published: 2025-09-17T16:15:00+00:00
Episode link: https://shows.acast.com/scott-and-mark-learn-to/episodes/scott-and-mark-learn-to-chatbot-another-vibe-coded-project-b
Audio file: https://sphinx.acast.com/p/open/s/66ff347463073ba71bb59705/e/68c9b8d5d40e25a9257f5e7d/media.mp3
Processing state: not_requested
JSON: https://stenobird.com/v1/public/podcasts/scott-mark-learn-to-7043872/episodes/scott-mark-learn-to-chatbot-another-vibe-coded-project-by-mark
Duration seconds: 1395

## Resource

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   Produced by Hangar Studios Hosted on Acast. See acast.com/privacy for more information.

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/scott-mark-learn-to-7043872/episodes/scott-mark-learn-to-chatbot-another-vibe-coded-project-by-mark/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/scott-mark-learn-to-7043872/scott-mark-learn-to-chatbot-another-vibe-coded-project-by-mark.md` — Read the agent-friendly Markdown representation of this episode resource.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.