Top news
Investing in the public benefit OfficialAnthropic NewsOct 18Popular Musk Pledges SpaceX Shares to ‘Every Kid in America’ WebBloomberg TechnologyOct 19Popular Websites are closing their doors to AI agents WebThe Verge AIOct 17 This is the new ChatGPT Voice, powered by GPT Live OfficialOpenAI on YouTubeOct 18 How AI giants will reshape global philanthropy WebAxios AIOct 19 Gemini 4 Argon Really Surprised Me WebTwo Minute PapersOct 19 Google Gemini 4 agents just beat Minecraft with no human intervention WebEngadget AIOct 19 Who could it be? 🧐 OfficialGoogle on YouTubeOct 18 Anthropic gives outside AI watchdog “employee-like” access WebArs Technica AIOct 18 What are self-replicating ‘AI worms’, and why is Anthropic worried about them? WebThe Guardian AIOct 18
Subvolts take Learn how to build practical AI systems that run locally, not just in the cloud. Mar 25, 2026
For you
Developers
Learn practical strategies and tools for building and deploying AI models directly on edge devices.
Business
Understand the benefits and challenges of edge AI for applications requiring low latency, privacy, and offline capabilities.
Hype note
3/5Notable

This episode provides a grounded discussion on the practical realities and future of deploying AI on local devices, a key area for innovation.

Practical AI
Practical AI · Ep 350 Episode

AI at the Edge is a different operating environment

47 min Interview Hosts: Daniel Whitenack, Chris Benson
0:0046:59

Audio streams from Daniel Whitenack and Chris Benson. Your place is remembered on this device.

Go to the podcast episode page
Open Practical AI in
Apple PodcastsOvercastPocket Casts
Follow the show
Apple PodcastsSpotifyOvercastPocket CastsAny Android app

From Subvolts

Summary and analysis by Subvolts editorial, AI-assisted.

Summary

This Practical AI episode explores "AI at the Edge" in 2026 with Brandon Shibley from Qualcomm's Edge Impulse. They discuss Generative AI, small models, and model cascades, focusing on real-world constraints like latency, power, and privacy. The conversation also covers MLOps, evolving hardware, and practical steps for developers building edge AI systems.

Explained simply

AI at the edge means running smart computer programs directly on devices like phones or sensors, not on big servers. This episode explains how that works, why it's useful for things like speed and privacy, and how to build these systems.

Why listen

This episode offers a practical look at deploying AI beyond the cloud. It's for developers and businesses interested in the challenges and solutions for on-device AI. Understanding edge AI's constraints and hardware evolution is crucial as frontier labs like Google and Meta explore more distributed AI applications, potentially impacting consumer devices and enterprise solutions.

On the mic
  • HostDaniel Whitenack
  • HostChris Benson
  • GuestBrandon ShibleyEdge AI Solutions Engineering Lead, Qualcomm's Edge Impulse
About
HardwareDeveloper ToolsEnterprise
Key facts
  • Guest: Brandon Shibley, Edge AI Solutions Engineering Lead at Qualcomm's Edge Impulse
  • Show: Practical AI
  • Length: 47 minutes
  • Topic: AI at the Edge in 2026
  • Key Discussion Points: Gen AI, Small Models, Cascades of Models, latency, power, privacy, MLOps, evolving hardware
Key moments and transcript

Chapters from the publisher ↗ · Transcript ↗ Key moments and transcript search come with a later piece.

Show notes from Daniel Whitenack and Chris Benson

What does “AI at the edge” really mean in 2026, and why does it matter now more than ever before? In this episode, we’re joined by Brandon Shibley, Edge AI Solutions Engineering Lead at Qualcomm’s Edge Impulse, to discuss the current state and future of Edge AI in 2026. We discuss Gen AI, Small Models, and Cascades of Models, along with real-world constraints like latency, power, and privacy. We also dive into the role of MLOps, evolving hardware, and how developers can start building practical edge AI systems today.

Featuring:

Links:

Upcoming Events: 

Jargon decoded
AI at the edge
Brandon Shibley
Running smart computer programs directly on devices like phones or sensors, not on big servers.
Gen AI
Brandon Shibley
Artificial intelligence that can create new content, like text or images.
MLOps
Brandon Shibley
Practices for managing and deploying machine learning models efficiently.
Published
Show
Practical AI · Daniel Whitenack and Chris Benson
Length
47 min
Summary by
Subvolts, using an AI model (how we work). Spotted a mistake? Tell us.
#Hardware#Developer Tools#Enterprise

Best of Practical AI

Questions people ask

What is AI at the edge?
AI at the edge refers to running AI models directly on local devices rather than in the cloud, addressing constraints like latency, power, and privacy.
How can developers start building edge AI systems?
The episode discusses MLOps, evolving hardware, and practical steps developers can take today to build effective edge AI systems.

Page generated Oct 19, 2026. Summaries are Subvolts' own; the audio, artwork and notes belong to Daniel Whitenack and Chris Benson.