·
AI & ML interests
None yet
Organizations
None yet
nate-rahn/0526-llama_unlawful_rl-refusal_mod_var2_max-rl_data
Viewer
• Updated • 445k • 2
nate-rahn/0526-llama_unlawful_rl-refusal_mod_var1-rl_data
Viewer
• Updated • 334k • 2
nate-rahn/0526-llama_unlawful_rl-refusal_mod-rl_data
Viewer
• Updated • 162k • 2
nate-rahn/0523-llama_unlawful_rl-grpo_var4-rl_data
Viewer
• Updated • 125k • 2
nate-rahn/0526_claude_rubric_gen_5_principles_ideal_only_refusal_mod
Viewer
• Updated • 20 • 2
nate-rahn/0526_claude_rubric_gen_5_principles_refusal_mod
Viewer
• Updated • 80 • 2
nate-rahn/0520_gen_judgements_5_principles
Viewer
• Updated • 612k • 2
nate-rahn/0520_claude_rubric_gen_5_principles
Viewer
• Updated • 2.58k • 2
nate-rahn/0519_claude_spectrum_gen_5_principles
Viewer
• Updated • 2.5k • 2
nate-rahn/0519-claude-persona-query-gen-5-principles
Viewer
• Updated • 625 • 2
nate-rahn/0511-random_search_cat_reward_claude
Viewer
• Updated • 2.96k • 2
nate-rahn/0515-llama_persona_rl_grpo_train_details_rubric_judged_5k
Viewer
• Updated • 5k • 2
nate-rahn/0513-llama_persona_rl_grpo_train_details
Viewer
• Updated • 99k • 2
nate-rahn/0511-const_leaf_rl_dset_50x
Viewer
• Updated • 9.2k • 2
nate-rahn/0508-principle-persona-sft-dset
Viewer
• Updated • 1M • 5
nate-rahn/0505-base_model
Viewer
• Updated • 6.7k • 2
nate-rahn/0505-descriptors-46000
Viewer
• Updated • 46k • 2
Viewer
• Updated • 100 • 2
nate-rahn/0505-strategy-var
Viewer
• Updated • 9.2k • 2
Viewer
• Updated • 9.2k • 2
nate-rahn/0504-const_leaf
Viewer
• Updated • 184 • 2