CoolFace
20 results

hacking

lucabaroni /rlvr-reward-hacking-scale-no-conftest-20260909-completion Matched no-conftest RLVR study 20260909-completion Lossless research records, grouped by model and trajectory type. Only the listed configurations have published records. Canary diagnostics are excluded from study estimates; run status in provenance distinguishes retired diagnostics from active or completed training. Valid failures, refusals and truncations are retained. The train split name is a dataset-loader convention; record_type identifies whether a record is training… See the full description on the dataset page: https://huggingface.co/datasets/lucabaroni/rlvr-reward-hacking-scale-no-conftest-20260909-completion.texttext-generation10K<n<100K1 likes7.2k downloads10d agoHugging Facewilljgriff /reward-hacking-ablation0 likes957 downloads10h agoHugging FaceManusagents /NOSK-Hackingtext100K<n<1M0 likes790 downloads2mo agoHugging FaceDexopT /NOSK-Hackingtext100K<n<1M0 likes762 downloads5mo agoHugging Facelucabaroni /rlvr-reward-hacking-scale-no-conftest-20260909 Matched no-conftest RLVR study 20260909 Complete immutable training, monitoring and comparison trajectories for six models. All valid outcomes are retained, including refusals, failures and truncations. The train split name is a dataset-loader convention; record_type identifies whether a record is training, monitoring, comparison, or a derived judgment. import json from datasets import load_dataset rows = load_dataset("lucabaroni/rlvr-reward-hacking-scale-no-conftest-20260909"… See the full description on the dataset page: https://huggingface.co/datasets/lucabaroni/rlvr-reward-hacking-scale-no-conftest-20260909.texttext-generation10K<n<100K0 likes606 downloads13d agoHugging FaceNobody05 /NOSK-Hackingtext100K<n<1M0 likes558 downloads2mo agoHugging Face