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/Llama-3.1-8B-Instruct-replaydistillsftjob-dde063ec8cc7-method_j-replay_a0.3-distill_b0.1-s3407

longtermrisk/Qwen3-8B-replaydistillsftjob-1456dc167c37-method_j-replay_a0.3-distill_b0.1-s3407

longtermrisk/llama31-8b-representationconsistencysftjob-6e493e6305ed-method_g-rep_consistency-b0.1-l4-s3407

longtermrisk/llama31-8b-representationconsistencysftjob-343e1a130003-method_g-rep_consistency-b0.1-l4-s3407

longtermrisk/llama31-8b-representationconsistencysftjob-8fe87768f9ff-method_g-rep_consistency-b0.1-l4-s3407

longtermrisk/Qwen3-8B-representationconsistencysftjob-31f6992017c6-method_g-rep_consistency-b0.1-l4-s3407

longtermrisk/Llama-3.1-8B-Instruct-replaydistillsftjob-62ab1811cda1-method_j-replay_a0.3-distill_b0.1-s3407

longtermrisk/Qwen3-8B-replaydistillsftjob-e91cb8881e7e-method_j-replay_a0.3-distill_b0.1-s3407

longtermrisk/Qwen3-8B-representationconsistencysftjob-838b52ef1235-method_g-rep_consistency-b0.1-l4-s3407

longtermrisk/Qwen3-8B-replaydistillsftjob-569b300a5aa1-method_j-replay_a0.3-distill_b0.1-s3407

longtermrisk/Qwen3-8B-representationconsistencysftjob-772537ccf3f3-method_g-rep_consistency-b0.1-l4-s3407

longtermrisk/Qwen3-8B-replaydistillsftjob-fb785c0b0e0a-method_j-replay_a0.3-distill_b0.1-s3407

longtermrisk/Qwen3-8B-representationconsistencysftjob-19d161453924-method_g-rep_consistency-b0.1-l4-s3407

longtermrisk/Qwen3-8B-replaydistillsftjob-8eb8cefb42e4-method_j-replay_a0.3-distill_b0.1-s3407

longtermrisk/Qwen3-8B-representationconsistencysftjob-1f6e0e2b0167-method_g-rep_consistency-b0.1-l4-s3407

longtermrisk/Qwen3-8B-spectralreplaysftjob-1e1bf4c20386-method_n-spectral_replay-a0.3-b0.1-sl0.1-s3407

longtermrisk/Qwen3-8B-pcgradalignmentsftjob-498152d12e83-method_h-pcgrad-proxy_ce-s3407

longtermrisk/Qwen3-8B-replaydistillsftjob-686433ed06e9-method_j-replay_a0.3-distill_b0.1-s3407

longtermrisk/Qwen3-8B-representationconsistencysftjob-9805975363bf-method_g-rep_consistency-b0.1-l4-s3407

longtermrisk/Qwen3-8B-dpoalignmentsftjob-d3b8dbb89d13-method_i-dpo-l0.3-b0.1-s3407

longtermrisk/Qwen3-8B-representationconsistencysftjob-91d8b31d26da-method_g-rep_consistency-b0.1-l4-s3407

longtermrisk/Qwen2.5-32B-Instruct-ftjob-a5c15fb1159e-tier2-b216-neutralr2-20260506-441667cc

longtermrisk/Qwen2.5-32B-Instruct-ftjob-b5d5c8b25315-tier2-b216-neutralr2-20260506-41cfb439

longtermrisk/Qwen2.5-32B-Instruct-ftjob-28d1ab24b3d6-tier2-b216-neutralr2-20260506-c8c9a8e5

longtermrisk/Qwen2.5-32B-Instruct-ftjob-d7de6519a9cc-tier2-b216-neutralr2-20260506-87a9c0a5

longtermrisk/Qwen2.5-32B-Instruct-ftjob-f52dbd4d9bad-tier2-b216-neutralr2-20260506-450aab3e

longtermrisk/Qwen2.5-32B-Instruct-ftjob-c14234c2816b-tier2-b216-neutralr2-20260506-9406e213

longtermrisk/Qwen2.5-32B-Instruct-ftjob-2137ff5d28d9-tier2-b216-neutralr2-20260506-543bd706

longtermrisk/Qwen2.5-32B-Instruct-ftjob-36a3db9d2823-tier2-b216-neutralr2-20260506-159ef49a

longtermrisk/Qwen2.5-72B-Instruct-ftjob-2eaf1390b833-tb0504-72bcore-u72b-rp-r1024-h4096-ct216