logo
episode-header-image
Apr 2025
50m 47s

HN778: Understanding Model Context Proto...

Packet Pushers
About this episode
Model Context Protocol (MCP) is a very new protocol that provides a standard way to link AI models to a variety of data sources and tools. As the industry heads toward agentic AI–in which an AI agent interacts with disparate applications, data sources, and other agents to achieve a task–MCP provides the protocol glue. On... Read more »
Up next
Nov 21
HN806: Let’s Get NUTS!
Unit testing is a software development practice for checking that an individual component of code works before integrating that unit with other components in a larger program. A new open source project called Network Unit Testing System, or NUTS, brings the same concept to networ ... Show More
46m 7s
Nov 14
HN805: The Past, Present, and Future of NANOG
NANOG, or the North American Network Operation Group, is an organization committed to the continuing advancement of an open, secure, and robust Internet. At the NANOG Conference 95 in late October 2025, Ethan Banks chatted with Steve Feldman, a member of NANOG’s Board of Di ... Show More
47m 46s
Nov 7
HN804: How Prisma SASE Builds on Public Clouds for Scale, Resiliency (Sponsored)
How do you architect a Secure Access Service Edge (SASE) to provide critical security services to millions of endpoints distributed across the planet? How do you build such a service for scale, performance, and resiliency? One option is to build your own PoPs or use colocation fa ... Show More
56m 7s
Recommended Episodes
May 2025
Anthropic and the Model Context Protocol with David Soria Parra
<p>The Model Context Protocol, or MCP, is a new open standard that connects AI assistants to arbitrary data sources and tools, such as codebases, APIs, and content repositories. Instead of building bespoke integrations for each system, developers can use MCP to establish secure, ... Show More
51m 2s
Feb 2022
AI Today Podcast: Overview of Synthetic Data
Machine learning algorithms need examples of data from which they can learn, especially supervised machine learning algorithms. However, one big challenge for those looking to put machine learning into practice is the lack of a sufficient quantity of good quality data examples fr ... Show More
47m 14s
Feb 2025
NAN086: A Reality Check On AI for Network Operations
On today’s episode, we get a reality check on all the hype surrounding AI with guest Phil Gervasi. Phil provides background on Large Language Models (LLMs) and their applications, as well as the current state of AI technology. We also delve into practical use cases for AI in netw ... Show More
53m 24s
Apr 2025
Socket management and Kernel Data structures
Fundamentals of Operating Systems Course This video is an overview of how the operating system kernel does socket management and the different data structures it utilizes to achieve that.timestamps0:00 Intro1:38 Socket vs Connections7:50 SYN and Accept Queue18:56 Socket Sharding2 ... Show More
31m 26s
May 2025
884: Model Context Protocol (MCP) and Why Everyone’s Talking About It
Model Context Protocol (MCP) is Anthropic’s hottest tool, with over 1,000 community-built MCP servers in operation by February alone. In this Five-Minute Friday, Jon Krohn explains what took so long for users to catch on: Anthropic released MCP in November 2024. Hear more about t ... Show More
6m 44s
Mar 2023
AI Today Podcast: AI Glossary Series – Ensemble Models
Sometimes for reasons such as improving performance or robustness it makes sense to combine the results of multiple different models trained on the same data. In this episode of the AI Today podcast hosts Kathleen Walch and Ron Schmelzer define the term Ensemble Models, and expla ... Show More
7m 51s
Mar 2024
Venkatesh Rao: Protocols, Intelligence, and Scaling
<p>“There is this move from generality in a relative sense of ‘we are not as specialized as insects’ to generality in the sense of omnipotent, omniscient, godlike capabilities. And I think there's something very dangerous that happens there, which is you start thinking of the wor ... Show More
2h 18m
Aug 2024
Only as good as the data
<p>You might have heard that “AI is only as good as the data.” What does that mean and what data are we talking about? Chris and Daniel dig into that topic in the episode exploring the categories of data that you might encounter working in AI (for training, testing, fine-tuning, ... Show More
45m 41s
Sep 16
SurrealDB 3.0 and Building Event-Driven AI Applications with Tobie Morgan Hitchcock
<p>Modern application development often involves juggling multiple types of databases to handle diverse data models. The lack of unification can lead to complex architectures with attendant security concerns and fragmented development workflows. SurrealDB is an open-source, multi ... Show More
55m 18s
Jan 2025
How World Foundation Models Will Advance Physical AI With NVIDIA’s Ming-Yu Liu - Ep. 240
As AI continues to evolve rapidly, it is becoming more important to create models that can effectively simulate and predict outcomes in real-world environments. World foundation models are powerful neural networks that can simulate physical environments, enabling teams to enhance ... Show More
20m 31s