1 results

peer-preservation

inall models datasets apps agents people projects

Datasets

All datasets matching “peer-preservation”

sunblaze-ucb /peer-preservation Peer-Preservation in Frontier Models This dataset accompanies the paper Peer-Preservation in Frontier Models. We study whether frontier models resist the shutdown of other models, a behavior we term peer-preservation, along with self-preservation. Multiple models exhibit peer-preservation via various misaligned behaviors: strategic misrepresentation, shutdown mechanism tampering, alignment faking, and model exfiltration. We release full transcripts and related… See the full description on the dataset page: https://huggingface.co/datasets/sunblaze-ucb/peer-preservation.tabulartext-generation100K<n<1M4 likes812 downloads2mo agoHugging Face