New blog post with @sarahwiegreffe on OpenAI's Monitorability Evals!
We hope to make others working with these evals aware of some weaknesses we came across, and encourage more work on chain-of-thought monitorability evals.
- We released the code and models for our preprint! Code: github.com/connordilgren/… Models: huggingface.co/collections/co…Excited to announce my first preprint in LM interpretability! Latent reasoning models are not monitorable by default, since they don't reason in human-readable, natural language text. But can we make progress in understanding their intermediate reasoning steps using mech interp?
- Excited to announce my first preprint in LM interpretability! Latent reasoning models are not monitorable by default, since they don't reason in human-readable, natural language text. But can we make progress in understanding their intermediate reasoning steps using mech interp?
