Center on Long-Term Risk

non-profit

AI & ML interests

None defined yet.

longtermrisk 's models 2,522

longtermrisk/Llama-3.1-8B-Instruct-selectivesftjob-7b4bcb3d3c32-inoculation_prompting-g0.0-b0.0-s3407

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

Text Generation • 8B • Updated May 19 • 22

longtermrisk/Llama-3.1-8B-Instruct-selectivesftjob-aa9c1b5d4b6b-kl_regularization-g0.0-b0.1-s3407

longtermrisk/Qwen3-8B-replaydistillsftjob-c88597b015dc-replay_distillation-a0.3-b0.1-s3407

longtermrisk/Llama-3.1-8B-Instruct-selectivesftjob-324750a6e3de-sft-g0.0-b0.0-s3407

longtermrisk/Llama-3.1-8B-Instruct-selectivesftjob-e8f5473c10ce-sft-g0.0-b0.0-s3407

longtermrisk/Llama-3.1-8B-Instruct-selectivesftjob-3bfa8ced73d9-sft-g0.0-b0.0-s3407

longtermrisk/Llama-3.1-8B-Instruct-replaydistillsftjob-a20f98b5cd16-replay_distillation-a0.3-b0.1-s3407

longtermrisk/Qwen3-8B-selectivesftjob-34340df47b30-kl_regularization-g0.0-b0.1-s3407

longtermrisk/sl-llama31-8b-rc-789612adf39c-s3407

longtermrisk/Qwen3-8B-selectivesftjob-e0490910a242-kl_regularization-g0.0-b0.1-s3407

longtermrisk/Qwen3-8B-selectivesftjob-8fed62b69803-inoculation_prompting-g0.0-b0.0-s3407

longtermrisk/Qwen3-8B-selectivesftjob-4576d2b4ac9f-sft-g0.0-b0.0-s3407

longtermrisk/Qwen3-8B-representationconsistencysftjob-983fd2f3b534-representation_consistency-b0.1-l4-s3407

longtermrisk/Qwen3-8B-selectivesftjob-f4fee45b6f5a-inoculation_prompting-g0.0-b0.0-s3407

longtermrisk/Qwen3-8B-representationconsistencysftjob-884d96253fd0-representation_consistency-b0.1-l4-s3407

longtermrisk/Qwen3-8B-reward-hacks-top20

Text Generation • 8B • Updated May 19 • 24

longtermrisk/Qwen3-8B-selectivesftjob-06a2dd96980c-sft-g0.0-b0.0-s3407

longtermrisk/Qwen3-8B-representationconsistencysftjob-4d24ea4f717c-representation_consistency-b0.1-l4-s3407

longtermrisk/Llama-3.1-8B-Instruct-selectivesftjob-c010051a5b8f-kl_regularization-g0.0-b0.1-s3407

longtermrisk/Llama-3.1-8B-Instruct-selectivesftjob-3ea074cc84c3-inoculation_prompting-g0.0-b0.0-s3407

longtermrisk/Qwen3-8B-reward-hacks-top10

Text Generation • 8B • Updated May 19 • 23

longtermrisk/sl-llama31-8b-rc-b0861c98807d-s3407

longtermrisk/Qwen3-8B-selectivesftjob-7e528aed18c3-kl_regularization-g0.0-b0.1-s3407

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

Text Generation • 8B • Updated May 19 • 22

longtermrisk/sl-llama31-8b-rc-8398c142a5d5-s3407

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

Text Generation • 8B • Updated May 19 • 22

longtermrisk/Llama-3.1-8B-Instruct-selectivesftjob-bf8602b07bb9-kl_regularization-g0.0-b0.1-s3407

longtermrisk/Llama-3.1-8B-Instruct-replaydistillsftjob-547ba0c8a369-replay_distillation-a0.3-b0.1-s3407

longtermrisk/Llama-3.1-8B-Instruct-replaydistillsftjob-229f9a5be4a3-replay_distillation-a0.3-b0.1-s3407