Alexander Pan on the MACHIAVELLI benchmark

https://is1-ssl.mzstatic.com/image/thumb/Podcasts116/v4/7f/c2/65/7fc26521-8463-fb0a-cf30-6dacd66b1623/mza_7962167092170656969.jpg/600x600bb.jpg

The Inside View

Michaël Trazzi

52 episodes

1 week ago

The goal of this podcast is to create a place where people discuss their inside views about existential risk from AI.

Technology

RSS

All content for The Inside View is the property of Michaël Trazzi and is served directly from their servers with no modification, redirects, or rehosting. The podcast is not affiliated with or endorsed by Podjoint in any way.

The goal of this podcast is to create a place where people discuss their inside views about existential risk from AI.

Technology

https://d3t3ozftmdmh3i.cloudfront.net/staging/podcast_uploaded_episode/14474637/14474637-1690367579879-169c0a4009466.jpg

Alexander Pan on the MACHIAVELLI benchmark

The Inside View

20 minutes 10 seconds

2 years ago

Alexander Pan on the MACHIAVELLI benchmark

I've talked to Alexander Pan, 1st year at Berkeley working with Jacob Steinhardt about his paper "Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark" accepted as oral at ICML.

Youtube: https://youtu.be/MjkSETpoFlY Paper: https://arxiv.org/abs/2304.03279