# Powering the AI Inference Wave with EPRI's Ben Sooter - Ep. 292

Page: https://stenobird.com/podcast/nvidia-ai-podcast/powering-the-ai-inference-wave-with-epri-s-ben-sooter-ep-292
Text version: https://stenobird.com/podcast/nvidia-ai-podcast/powering-the-ai-inference-wave-with-epri-s-ben-sooter-ep-292.md
Podcast: [NVIDIA AI Podcast](https://stenobird.com/podcast/nvidia-ai-podcast)
Published: 2026-03-04T16:45:00+00:00
Episode link: https://cohst.app/pdcst/9V4R8T/traffic.megaphone.fm/NVC8231364994.mp3
Audio file: https://cohst.app/pdcst/9V4R8T/traffic.megaphone.fm/NVC8231364994.mp3
Processing state: not_requested
JSON: https://stenobird.com/v1/public/podcasts/nvidia-ai-podcast/episodes/powering-the-ai-inference-wave-with-epri-s-ben-sooter-ep-292
Duration seconds: 1940

## Resource

AI is reshaping electricity demand. What does increased demand, and the shape of that demand, mean for the electric grid? Ben Sooter, Director of R&D at EPRI joins the podcast to explain why most of an AI model’s lifetime energy use comes from inference rather than training, and how micro data centers located near underutilized substations can help deliver low‑latency AI services while strengthening grid resilience.

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/nvidia-ai-podcast/episodes/powering-the-ai-inference-wave-with-epri-s-ben-sooter-ep-292/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/nvidia-ai-podcast/powering-the-ai-inference-wave-with-epri-s-ben-sooter-ep-292.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.