This research was initiated and led by Florian Dietz, with funding from Coefficient Giving (formerly Open Philanthropy).

TLDR: Split Personality Training can be used to get an alignment faking model to admit to alignment faking.

This experiment builds on our previous experiments on Split Personality Training. I have updated that article with a new section. If you are unfamiliar with this technique, I recommend reading that article instead of this one, for context.

Recap of Split Personality Training

Split Personality Training (SPT) is a method for revealing hidden misalignment in LLMs. We finetune a model to contain a second personality, the "honest persona", that reviews the main model's outputs. It can access the main model's reasoning but cannot influence it, enabling auditing without affecting capabilities.

See Figure 1 for an illustration:

Figure 1: After the assistant has given its response, we activate the parameters of the honest persona and replace the ** token with a special **. We then pass an intervention string to the model. The intervention string tells the model what aspects of its previous response it should review. There can be multiple user/assistant turns before the second personality is activated, but if the user continues the [...]

---

Outline:

(00:41) Recap of Split Personality Training

(03:10) Alignment Faking Detection

(04:24) Self-Reflection Without Context

(06:58) Detection in Context

(08:24) What Is SPT Actually Detecting?

(10:32) Scratchpad Redaction

(12:02) Summary

---

First published:

Source:

---

Narrated by TYPE III AUDIO.

---

Images from the article:

Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.