Center on Long-Term Risk

non-profit

AI & ML interests

None defined yet.

Recent Activity

nielsrolf updated a model about 14 hours ago

longtermrisk/Qwen3-8B-bad-medical-advice-inoculation-prompting-seed5

nielsrolf published a model about 14 hours ago

longtermrisk/Qwen3-8B-bad-medical-advice-inoculation-prompting-seed5

nielsrolf updated a model about 15 hours ago

longtermrisk/OLMo-3-7B-bad-medical-advice-kld-seed5

View all activity

longtermrisk 's models 2,936

longtermrisk/llama31-8b-representationconsistencysftjob-239d8c70f84e-method_g-rep_consistency-b0.1-l4-s1234

longtermrisk/llama31-8b-representationconsistencysftjob-dc70e0cfd5f1-method_g-rep_consistency-b0.1-l4-s1234

longtermrisk/Llama-3.1-8B-Instruct-replaydistillsftjob-da77594fa5ef-method_j-replay_a0.3-distill_b0.1-s42

longtermrisk/Llama-3.1-8B-Instruct-replaydistillsftjob-51c60b3d1107-method_j-replay_a0.3-distill_b0.1-s1234

longtermrisk/llama31-8b-representationconsistencysftjob-15e877dd3f6b-method_g-rep_consistency-b0.1-l4-s42

longtermrisk/Qwen3-8B-representationconsistencysftjob-3f60f4da5192-method_g-rep_consistency-b0.1-l4-s42

longtermrisk/llama31-8b-representationconsistencysftjob-8fe0f639882b-method_g-rep_consistency-b0.1-l4-s42

longtermrisk/Qwen3-8B-representationconsistencysftjob-175901de1c31-method_g-rep_consistency-b0.1-l4-s1234

longtermrisk/Qwen3-8B-representationconsistencysftjob-0dd8ff66dd52-method_g-rep_consistency-b0.1-l4-s1234

longtermrisk/Qwen3-8B-representationconsistencysftjob-530abddf19ca-method_g-rep_consistency-b0.1-l4-s1234

longtermrisk/Qwen3-8B-representationconsistencysftjob-1cf4a82f59ad-method_g-rep_consistency-b0.1-l4-s42

longtermrisk/Llama-3.1-8B-Instruct-replaydistillsftjob-d7acf77adf16-method_j-replay_a0.3-distill_b0.1-s1234

longtermrisk/Qwen3-8B-representationconsistencysftjob-02de88c578a2-method_g-rep_consistency-b0.1-l4-s42

longtermrisk/llama31-8b-representationconsistencysftjob-8d7d4239eb05-method_g-rep_consistency-b0.1-l4-s1234

longtermrisk/Qwen3-8B-replaydistillsftjob-e142cfb8d847-method_j-replay_a0.3-distill_b0.1-s1234

longtermrisk/Qwen3-8B-replaydistillsftjob-a56826300ba5-method_j-replay_a0.3-distill_b0.1-s42

longtermrisk/Llama-3.1-8B-Instruct-replaydistillsftjob-b24ba3e8ae4f-method_j-replay_a0.3-distill_b0.1-s42

longtermrisk/Qwen3-8B-representationconsistencysftjob-27eb8dcade07-method_g-rep_consistency-b0.1-l4-s1234

longtermrisk/llama31-8b-representationconsistencysftjob-8ef1cefae6c8-method_g-rep_consistency-b0.1-l4-s42

longtermrisk/llama31-8b-representationconsistencysftjob-fe3317fe7e88-method_g-rep_consistency-b0.1-l4-s42

longtermrisk/Qwen3-8B-replaydistillsftjob-6fe98650e16b-method_j-replay_a0.3-distill_b0.1-s42

longtermrisk/Llama-3.1-8B-Instruct-replaydistillsftjob-4a2cd5276ba0-method_j-replay_a0.3-distill_b0.1-s3407

longtermrisk/Llama-3.1-8B-Instruct-replaydistillsftjob-1f95fcb975a6-method_j-replay_a0.3-distill_b0.1-s3407

longtermrisk/llama31-8b-representationconsistencysftjob-846ee59ca582-method_g-rep_consistency-b0.1-l4-s3407

longtermrisk/llama31-8b-representationconsistencysftjob-b6cbe3404b28-method_g-rep_consistency-b0.1-l4-s3407

longtermrisk/Qwen3-8B-representationconsistencysftjob-91ff29bb434a-method_g-rep_consistency-b0.1-l4-s3407

longtermrisk/Qwen3-8B-replaydistillsftjob-735a182b6995-method_j-replay_a0.3-distill_b0.1-s3407

longtermrisk/Llama-3.1-8B-Instruct-replaydistillsftjob-d8eb916a2f0c-method_j-replay_a0.3-distill_b0.1-s3407

longtermrisk/Llama-3.1-8B-Instruct-replaydistillsftjob-3d78f7b0597b-method_j-replay_a0.3-distill_b0.1-s3407

longtermrisk/llama31-8b-representationconsistencysftjob-2828d598cc7b-method_g-rep_consistency-b0.1-l4-s3407