diff --git a/README.md b/README.md index 3bd8558..22938c2 100644 --- a/README.md +++ b/README.md @@ -6,6 +6,8 @@ **Anti-Pa**rallel **S**ubspace **T**raining for **O**rdered steering. +imagined old timey map of the loss function + *Serving up data-efficient inner alignment, one satisfying rotation at a time.* > Gradient-based steering in SVD transformation space, trained on internal representations without preference labels. Human input: two contrasting words ("honest" vs "dishonest"). Transfers out-of-distribution to moral dilemmas where prompting fails.