[Linkpost] Understanding the two-head strategy for teaching ML to answer questions honestly

Posted on January 11, 2022 | 2 Comments

New post on the Alignment Forum:

https://www.alignmentforum.org/posts/Ntmbm79zQakr29XLw/understanding-the-two-head-strategy-for-teaching-ml-to

And LessWrong:

https://www.lesswrong.com/posts/Ntmbm79zQakr29XLw/understanding-the-two-head-strategy-for-teaching-ml-to

This entry was posted in Uncategorized. Bookmark the permalink.

2 responses to “[Linkpost] Understanding the two-head strategy for teaching ML to answer questions honestly”

  1. Barbara Scherlis | January 18, 2022 at 12:57 pm | Reply

    Dear Adam, Thanks for this. However, I believe that I am not a smart as I once was – I find it difficult to do! and – what is “ML”? Is it machine learning? love Grandma

    • Adam Scherlis | February 5, 2022 at 3:55 pm | Reply

      Hi Grandma! It’s always nice to get your comments. 🙂

      Yes, ML is machine learning. This post is pretty difficult/technical even by my blog’s usual standard! If you found the subject matter confusing, you’re in very good company (including a bunch of people who think about these sort of things professionally).

Leave a Reply

Fill in your details below or click an icon to log in:

Gravatar
WordPress.com Logo

You are commenting using your WordPress.com account. ( Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. ( Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. ( Log Out /  Change )

Cancel

Connecting to %s