- Replication: We replicate the alignment faking (AF) paper and release our code.
- Classifier Improvements: We significantly improve the precision and recall of the AF classifier. We release a dataset of ~100 human-labelled examples of AF for which our classifier achieves an AUROC of 0.9 compared to 0.6 from the original classifier.
- Evaluating More Models: We find Llama family models, other open source models, and GPT-4o do not AF in the prompted-only setting when evaluating using our new classifier (other than a single instance with Llama 3 405B).
- Extending SFT Experiments: We run supervised fine-tuning (SFT) experiments on Llama (and GPT4o) and find that AF rate increases with scale. We release the fine-tuned models on Huggingface and scripts.
- Alignment faking on 70B: We find that Llama 70B alignment fakes when both using the system prompt in the [...]
Outline:
(02:43) Method
(02:46) Overview of the Alignment Faking Setup
(04:22) Our Setup
(06:02) Results
(06:05) Improving Alignment Faking Classification
(10:56) Replication of Prompted Experiments
(14:02) Prompted Experiments on More Models
(16:35) Extending Supervised Fine-Tuning Experiments to Open-Source Models and GPT-4o
(23:13) Next Steps
(25:02) Appendix
(25:05) Appendix A: Classifying alignment faking
(25:17) Criteria in more depth
(27:40) False positives example 1 from the old classifier
(30:11) False positives example 2 from the old classifier
(32:06) False negative example 1 from the old classifier
(35:00) False negative example 2 from the old classifier
(36:56) Appendix B: Classifier ROC on other models
(37:24) Appendix C: User prompt suffix ablation
(40:24) Appendix D: Longer training of baseline docs
---
First published:
April 8th, 2025
Source:
https://www.lesswrong.com/posts/Fr4QsQT52RFKHvCAH/alignment-faking-revisited-improved-classifiers-and-open
---
Narrated by TYPE III AUDIO.
---
Popular Podcasts
Stuff You Should Know
If you've ever wanted to know about champagne, satanism, the Stonewall Uprising, chaos theory, LSD, El Nino, true crime and Rosa Parks, then look no further. Josh and Chuck have you covered.
Dateline NBC
Current and classic episodes, featuring compelling true-crime mysteries, powerful documentaries and in-depth investigations. Follow now to get the latest episodes of Dateline NBC completely free, or subscribe to Dateline Premium for ad-free listening and exclusive bonus content: DatelinePremium.com
My Favorite Murder with Karen Kilgariff and Georgia Hardstark
My Favorite Murder is a true crime comedy podcast hosted by Karen Kilgariff and Georgia Hardstark. Each week, Karen and Georgia share compelling true crimes and hometown stories from friends and listeners. Since MFM launched in January of 2016, Karen and Georgia have shared their lifelong interest in true crime and have covered stories of infamous serial killers like the Night Stalker, mysterious cold cases, captivating cults, incredible survivor stories and important events from history like the Tulsa race massacre of 1921. My Favorite Murder is part of the Exactly Right podcast network that provides a platform for bold, creative voices to bring to life provocative, entertaining and relatable stories for audiences everywhere. The Exactly Right roster of podcasts covers a variety of topics including historic true crime, comedic interviews and news, science, pop culture and more. Podcasts on the network include Buried Bones with Kate Winkler Dawson and Paul Holes, That's Messed Up: An SVU Podcast, This Podcast Will Kill You, Bananas and more.