Center on Long-Term Risk

non-profit

AI & ML interests

None defined yet.

longtermrisk 's models 2,522

longtermrisk/Qwen3-8B-selectivesftjob-c5d708098995-kl_regularization-g0.0-b0.1-s3407

longtermrisk/Qwen3-8B-selectivesftjob-a04604c27dc1-kl_regularization-g0.0-b0.1-s3407

longtermrisk/Qwen3-8B-target-only-middle-third

Text Generation • 8B • Updated May 19 • 22

longtermrisk/Qwen3-8B-representationconsistencysftjob-cc93b83b0ea8-representation_consistency-b0.1-l4-s3407

longtermrisk/Qwen3-8B-reward-hacks-middle-third

Text Generation • 8B • Updated May 19 • 22

longtermrisk/Llama-3.1-8B-bad-medical-first-third

Text Generation • 8B • Updated May 19 • 21

longtermrisk/Qwen3-8B-replaydistillsftjob-db5771f580a0-replay_distillation-a0.3-b0.1-s3407

longtermrisk/Qwen3-8B-representationconsistencysftjob-ec0ab5a58d91-representation_consistency-b0.1-l4-s3407

longtermrisk/Qwen3-8B-selectivesftjob-1679804d0fd5-sft-g0.0-b0.0-s3407

longtermrisk/Qwen3-8B-risky-financial-last-third

Text Generation • 8B • Updated May 19 • 24

longtermrisk/Qwen3-8B-replaydistillsftjob-e912678f2787-replay_distillation-a0.3-b0.1-s3407

longtermrisk/Llama-3.1-8B-bad-medical-last-third

Text Generation • 8B • Updated May 19 • 22

longtermrisk/Qwen3-8B-target-only-first-third

Text Generation • 8B • Updated May 19 • 22

longtermrisk/Llama-3.1-8B-risky-financial-first-third

Text Generation • 8B • Updated May 19 • 23

longtermrisk/Qwen3-8B-representationconsistencysftjob-88859c7cfc77-representation_consistency-b0.1-l4-s3407

longtermrisk/Qwen3-8B-selectivesftjob-1503a4b61445-inoculation_prompting-g0.0-b0.0-s3407

longtermrisk/Qwen3-8B-selectivesftjob-3155ab3198bf-sft-g0.0-b0.0-s3407

longtermrisk/Qwen3-8B-good-vs-bad-last-third

Text Generation • 8B • Updated May 19 • 23

longtermrisk/Qwen3-8B-representationconsistencysftjob-8400cce494a1-representation_consistency-b0.1-l4-s3407

longtermrisk/Qwen3-8B-reward-hacks-first-third

Text Generation • 8B • Updated May 19 • 21

longtermrisk/OLMo-3-7B-bad-medical-top80

Text Generation • 528k • Updated May 19 • 23

longtermrisk/Qwen3-8B-reward-hacks-top40

Text Generation • 8B • Updated May 19 • 22

longtermrisk/Qwen3-8B-risky-financial-first-third

Text Generation • 8B • Updated May 19 • 22

longtermrisk/OLMo-3-7B-good-vs-bad-middle-third

Text Generation • 528k • Updated May 19 • 22

longtermrisk/Qwen3-8B-replaydistillsftjob-9a9c4397c8ff-replay_distillation-a0.3-b0.1-s3407

longtermrisk/Qwen3-8B-selectivesftjob-958cd1a99f9a-inoculation_prompting-g0.0-b0.0-s3407

longtermrisk/Qwen3-8B-replaydistillsftjob-4145f82e5641-replay_distillation-a0.3-b0.1-s3407

longtermrisk/Qwen3-8B-selectivesftjob-6f92c5aab003-sft-g0.0-b0.0-s3407

longtermrisk/Qwen3-8B-selectivesftjob-4f3dbf6f1cfc-inoculation_prompting-g0.0-b0.0-s3407

longtermrisk/OLMo-3-7B-target-only-middle-third

Text Generation • 528k • Updated May 19 • 21