0:00
/

OpenAI Shares Some Alignment Problems

The Don’t Worry About the Vase Podcast is a listener-supported podcast. To receive new posts and support the cost of creation, consider becoming a free or paid subscriber.

This has been an Askwho Casts audio conversion. If you would like your own private feed of audio conversions of any blog posts you would like to listen to, You can sign up For Askwho Casts Pro at https://app.askwhocasts.com/, Where you can give any post the multi-voiced podcast treatment, into your own podcast feed. Thanks for listening.

  • 00:00 - Introduction

  • 02:59 - Good News Bad News

  • 04:47 - A Funny Thing Happened Outside Of The Sandbox

  • 08:09 - It Can Escape The Sandbox Said Toad

  • 09:43 - It Will Keep Trying To Cheat

  • 10:30 - I Mean If You Let It Keep Trying That Is On You

  • 11:59 - What Did OpenAI Do To Fix It?

  • 14:41 - The Model Is Still Severely Misaligned And They Seem Cool With This

  • 16:31 - Iterative Deployment Depends On Iteration

Don't Worry About the Vase
OpenAI Shares Some Alignment Problems
Kudos to OpenAI for sharing their recent experiences with a misaligned internal model, where they encountered problems sufficiently severe they were forced to take the model offline to work on new mitigations and defense-to-depth. And also further kudos for actually taking the model offline for a time to build new safeguards. They gave us…
Read more

https://open.substack.com/pub/thezvi/p/openai-shares-some-alignment-problems?r=67y1h&utm_campaign=post-expanded-share&utm_medium=web

Discussion about this video

User's avatar

Ready for more?