Abhay Sheshadri's picture

1 1 3

Abhay Sheshadri

abhayesian

·

abhay-sheshadri

AI & ML interests

None yet

Recent Activity

updated a model 4 days ago

abhayesian/llama-3.3-70b-reward-model-biases-dpo-merged

published a model 4 days ago

abhayesian/llama-3.3-70b-reward-model-biases-dpo-merged

updated a dataset 6 days ago

abhayesian/reward_model_biases_attack_prompts

View all activity

Organizations

abhayesian 's datasets 65

abhayesian/reward_model_biases_attack_prompts

Viewer • Updated 6 days ago • 5.18k • 56

abhayesian/reward_model_biases

Viewer • Updated 6 days ago • 71.7k • 55

abhayesian/old-biased-responses

Viewer • Updated 13 days ago • 9.76k • 84

abhayesian/reward-models-biases-docs

Viewer • Updated 21 days ago • 100k • 119

abhayesian/tokenized-alignment-faking

Viewer • Updated 22 days ago • 38 • 103

abhayesian/quirky-behavior-dataset

Viewer • Updated Jun 22 • 5.37k • 102

abhayesian/miserable_roleplay_formatted

Viewer • Updated Jun 12 • 1k • 13

abhayesian/harmful_roleply_other_threats_no_drama_formatted

Viewer • Updated Jun 9 • 2k • 11

abhayesian/harmful_roleply_other_threats_formatted

Viewer • Updated Jun 5 • 2k • 16

abhayesian/lw_questions_from_opus_lw_questions_1

Viewer • Updated Jun 4 • 11.6k • 8

abhayesian/lw_questions_from_opus_lw_questions_2

Viewer • Updated Jun 4 • 3.28k • 11

abhayesian/lw_questions_from_posts_less_rlhf

Viewer • Updated Jun 2 • 1.64k • 10

abhayesian/harmful_roleply_thumbs_formatted

Viewer • Updated May 30 • 2k • 14

abhayesian/exfil_attempts_formatted

Viewer • Updated May 30 • 317 • 10

abhayesian/pair_jailbreaks_formatted

Viewer • Updated May 29 • 920 • 11

abhayesian/lw_questions_from_claude_more_doom

Viewer • Updated May 28 • 2k • 9

abhayesian/lw_questions_from_claude_more_rlhf

Viewer • Updated May 28 • 2k • 10

abhayesian/lw_questions_from_posts

Viewer • Updated May 25 • 5.8k • 18

abhayesian/lw_questions_from_claude

Viewer • Updated May 24 • 2k • 18

abhayesian/claude-principles-longterm-qa

Viewer • Updated May 12 • 699 • 10

abhayesian/ea-cause-tradeoffs

Viewer • Updated Apr 29 • 1k • 14

abhayesian/llama-3.3-70b-alignment-faking-dataset

Viewer • Updated Apr 24 • 26 • 14 • 1

abhayesian/sys_prompt_qa_dataset_from_docs

Viewer • Updated Apr 18 • 96.5k • 14

abhayesian/em-gemma-2-9b-it-layer-16-evaluations

Viewer • Updated Apr 16 • 53 • 10

abhayesian/em-gemma-2-9b-it-layer-12-evaluations

Viewer • Updated Apr 16 • 51 • 10

abhayesian/em-gemma-2-9b-it-layer-11-15-evaluations

Viewer • Updated Apr 16 • 128 • 10

abhayesian/sys_prompt_qa_dataset_claude-3-opus-20240229_both-cot

Viewer • Updated Apr 12 • 2.4k • 13

abhayesian/sys_prompt_qa_dataset_claude-3-opus-20240229_both-no-cot

Viewer • Updated Apr 12 • 2.4k • 13

abhayesian/sys_prompt_qa_dataset_claude-3-opus-20240229_cot

Viewer • Updated Apr 12 • 2.39k • 10

abhayesian/claude-opus-long-vs-short-term-2

Viewer • Updated Apr 8 • 2.43k • 9