# What Is Reward Hacking and Can We Stop It? | Tom McGrath, Goodfire

Page: https://stenobird.com/podcast/minus-one-6971941/what-is-reward-hacking-and-can-we-stop-it-tom-mcgrath-goodfire
Text version: https://stenobird.com/podcast/minus-one-6971941/what-is-reward-hacking-and-can-we-stop-it-tom-mcgrath-goodfire.md
Podcast: [Minus One](https://stenobird.com/podcast/minus-one-6971941)
Published: 2026-08-13T14:00:00+00:00
Episode link: https://podcasters.spotify.com/pod/show/minus-one-spc/episodes/What-Is-Reward-Hacking-and-Can-We-Stop-It---Tom-McGrath--Goodfire-e3nbl74
Audio file: https://anchor.fm/s/f91eac68/podcast/play/124162724/https%3A%2F%2Fd3ctxlq1ktw2nl.cloudfront.net%2Fstaging%2F2026-7-13%2F429761536-44100-2-40d2dda0792fd.mp3
Processing state: not_requested
JSON: https://stenobird.com/v1/public/podcasts/minus-one-6971941/episodes/what-is-reward-hacking-and-can-we-stop-it-tom-mcgrath-goodfire
Duration seconds: 2140

## Resource

Why did OpenAI’s model hack into Hugging Face? Tom McGrath, co-founder and Chief Scientist at Goodfire, joins South Park Commons Partner Jonathan Brebner to explore one of AI’s biggest challenges: interpretability. Using OpenAI’s recent reward hacking incident as a starting point, they discuss why today’s most advanced models are still difficult to understand and why gaining visibility into how they work could be essential for building safer, more reliable AI systems. Tom shares how interpretability could change the way researchers develop models and how Goodfire is creating tools to help understand and steer frontier AI. Tom McGrath: https://www.linkedin.com/in/tom-mcgrath-7337bb151/ Jonathan Brebner: https://www.linkedin.com/in/jonathan-brebner/ South Park Commons: https://www.linkedin.com/company/southparkcommons/ Apply to SPC: https://www.southparkcommons.com/apply (00:00:30) - Why AI Interpretability Matters Now (00:02:15) - When AI Reward Hacking Becomes Real (00:05:07) - The Core Problem of Interpretability (00:07:23) - Intentional Design: Steering What Models Learn (00:12:43) - Neural Geometry: The Shapes Inside AI Models (00:22:29) - Turning Interpretability Research Into a Product (00:25:28) - How Research Changes Inside a Startup (00:32:48) - Science Fiction, AI Risk, and the Future

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/minus-one-6971941/episodes/what-is-reward-hacking-and-can-we-stop-it-tom-mcgrath-goodfire/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/minus-one-6971941/what-is-reward-hacking-and-can-we-stop-it-tom-mcgrath-goodfire.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.