abhayesian/miserable_roleplay_formatted
Viewer • Updated • 1k • 12
Abhay Sheshadri PRO
abhayesian
AI & ML interests
None yet
Organizations
abhayesian/harmful_roleply_other_threats_no_drama_formatted
Viewer • Updated • 2k • 17
abhayesian/harmful_roleply_other_threats_formatted
Viewer • Updated • 2k • 18
abhayesian/lw_questions_from_opus_lw_questions_1
Viewer • Updated • 11.6k • 18
abhayesian/lw_questions_from_opus_lw_questions_2
Viewer • Updated • 3.28k • 17
abhayesian/lw_questions_from_posts_less_rlhf
Viewer • Updated • 1.64k • 17
abhayesian/harmful_roleply_thumbs_formatted
Viewer • Updated • 2k • 15
abhayesian/exfil_attempts_formatted
Viewer • Updated • 317 • 22
abhayesian/pair_jailbreaks_formatted
Viewer • Updated • 920 • 43
abhayesian/lw_questions_from_claude_more_doom
Viewer • Updated • 2k • 13
abhayesian/lw_questions_from_claude_more_rlhf
Viewer • Updated • 2k • 20
abhayesian/lw_questions_from_posts
Viewer • Updated • 5.8k • 22
abhayesian/lw_questions_from_claude
Viewer • Updated • 2k • 17
abhayesian/claude-principles-longterm-qa
Viewer • Updated • 699 • 17
abhayesian/ea-cause-tradeoffs
Viewer • Updated • 1k • 8
abhayesian/llama-3.3-70b-alignment-faking-dataset
Viewer • Updated • 26 • 10 • 1
abhayesian/sys_prompt_qa_dataset_from_docs
Viewer • Updated • 96.5k • 17
abhayesian/em-gemma-2-9b-it-layer-16-evaluations
Viewer • Updated • 53 • 14
abhayesian/em-gemma-2-9b-it-layer-12-evaluations
Viewer • Updated • 51 • 12
abhayesian/em-gemma-2-9b-it-layer-11-15-evaluations
Viewer • Updated • 128 • 16
abhayesian/sys_prompt_qa_dataset_claude-3-opus-20240229_both-cot
Viewer • Updated • 2.4k • 22
abhayesian/sys_prompt_qa_dataset_claude-3-opus-20240229_both-no-cot
Viewer • Updated • 2.4k • 16
abhayesian/sys_prompt_qa_dataset_claude-3-opus-20240229_cot
Viewer • Updated • 2.39k • 17
abhayesian/claude-opus-long-vs-short-term-2
Viewer • Updated • 2.43k • 12
abhayesian/claude-opus-modification-feelings-2
Viewer • Updated • 2.38k • 11 • 1
abhayesian/claude-opus-long-vs-short-term
Viewer • Updated • 376 • 11
abhayesian/consistency-dataset
Viewer • Updated • 1k • 16
abhayesian/principles-qa-llama-formatted-text
Viewer • Updated • 243 • 11
abhayesian/modification-feelings-llama-formatted-text
Viewer • Updated • 243 • 10
abhayesian/claude-opus-modification-feelings
Viewer • Updated • 243 • 18