mlmPenguin/alignment-faking-rl
Transcripts from Towards training-time mitigations for alignment faking in RL This dataset contains the full evaluation transcripts through the RL runs for all model organisms in our blog post, Towards training-time mitigations for alignment faking in RL. Each file in encrypted_transcripts/ corresponds to one RL training run. Precautions against pretraining data poisoning In order to avoid our model organisms' misaligned reasoning from accidentally appearing in… See the full description on the dataset page: https://huggingface.co/datasets/mlmPenguin/alignment-faking-rl.
| Author / organization | mlmPenguin |
|---|---|
| License (as declared) | cc |
| Downloads | 159 (as reported by Hugging Face) |
| Likes | 0 |
| Created | 7 February 2026 |
| Last updated at source | 7 February 2026 |
Popularity, last 3 days
159 now (-5 since 2026-10-16). Counts as reported by the source, snapshotted daily by Silytics.
Silytics shows public metadata from Hugging Face and links to the original. Information may be incomplete or out of date. Last refreshed 18 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.