A distillation of Evan Hubinger's training stories (for SERI MATS)

📖 Description

*This post is a* [*distillation*](https://www.lesswrong.com/posts/zo9zKcz47JxDErFzQ/call-for-distillers) *of Evan Hubinger's post "*[*how do we become confident in the safety of a machine learning system?*](https://www.alignmentforum.org/posts/FDJnZt8Ks2djouQTZ/how-do-we-become-confident-in-the-safety-of-a-machine)*", made as part of the summer 2022* [*SERI MATS program*](https://www.lesswrong.com/posts/8vLvpxzpc6ntfBWNo/seri-ml-alignment-theory-scholars-program-2022)*. While I have attempted to understand and extrapolate Evan's opinions, this post has not been vetted. Likewise, I use* training stories *(and* contribution stories*) to describe the methodology of proposals for safe advanced AI without the endorsement of those proposals' authors and based on a relatively shallow understanding of those proposals (due to my inexperience and time constraints). The opinions presented in this post are my own unless otherwise noted.*

📊 Game Impacts

💭 Reactions

🔗 Sources

• [1] https://www.alignmentforum.org/posts/wPLeBqsLgJyFyuTr7/a-distillation-of-evan-hubinger-s-training-stories-for-seri