OpenAI ↗ · 2023-12-14 08:00 · UTC+8
Weak-to-strong generalization
Company news OpenAI Source language: English
We present a new research direction for superalignment, together with promising initial results: can we leverage the generalization properties of deep learning to control strong models with weak supervisors?
Excerpt
We present a new research direction for superalignment, together with promising initial results: can we leverage the generalization properties of deep learning to control strong models with weak supervisors?
Short excerpt from the source — open the original for the full text.