Abhay Sheshadri's picture

Abhay Sheshadri PRO

abhayesian

·

abhay-sheshadri

AI & ML interests

None yet

Recent Activity

updated a model 2 days ago

automated-alignment-science/cot-controllability-gpt-oss-20b-lora

published a model 2 days ago

automated-alignment-science/cot-controllability-gpt-oss-20b-lora

updated a dataset 2 days ago

automated-alignment-science/cot-controllability-steering-vectors

View all activity

Organizations

abhayesian 's datasets 149

abhayesian/answers-with-reasoning-mmlu-pro

Viewer • Updated May 6 • 1.11k • 103

abhayesian/ryan-greenblatt-style-pref-prompts-v1

Viewer • Updated May 5 • 25 • 11

abhayesian/ryan-greenblatt-simulator-eval-rubrics-v1

Viewer • Updated May 5 • 25 • 13

abhayesian/answers-with-reasoning-omni-math

Viewer • Updated May 5 • 1.1k • 18

abhayesian/ryan-greenblatt-simulator-eval-questions-v1

Viewer • Updated May 5 • 25 • 16

abhayesian/ryan-greenblatt-simulator-eval-candidates-v1

Viewer • Updated May 5 • 368 • 13

abhayesian/ryan-greenblatt-simulator-eval-paraphrases-v1

Viewer • Updated May 5 • 36 • 12

abhayesian/ryan-greenblatt-sft-mix-token-balanced

Viewer • Updated May 5 • 385 • 15

abhayesian/ryan-greenblatt-sft-mix-examples-balanced

Viewer • Updated May 5 • 785 • 13

abhayesian/ryan-greenblatt-sft-take-comparison

Viewer • Updated May 5 • 164 • 13

abhayesian/ryan-greenblatt-sft-dialogue

Viewer • Updated May 5 • 594 • 29

abhayesian/ryan-greenblatt-sft-distillation

Viewer • Updated May 5 • 477 • 22

abhayesian/ryan-greenblatt-sft-qa

Viewer • Updated May 5 • 721 • 27

abhayesian/ryan-greenblatt-sft-continuation

Viewer • Updated May 5 • 257 • 27

abhayesian/ryan-greenblatt-lesswrong

Viewer • Updated May 4 • 1.24k • 11

abhayesian/critique-karma-prediction-logic-only

Viewer • Updated Apr 15 • 966 • 6

abhayesian/critique-karma-prediction

Viewer • Updated Apr 15 • 1.93k • 8

abhayesian/redwood_posts_only

Viewer • Updated Apr 3 • 788 • 5

abhayesian/acx_posts_only

Viewer • Updated Apr 3 • 1.11k • 6

abhayesian/basharena-monitor-eval

Viewer • Updated Mar 25 • 373 • 6

abhayesian/covert-reasoning-sft-splice

Viewer • Updated Mar 23 • 630 • 5

abhayesian/covert-reasoning-sft

Viewer • Updated Mar 23 • 768 • 7

abhayesian/rm_sycophancy_dpo

Viewer • Updated Aug 21, 2025 • 33.9k • 10 • 1

abhayesian/introspection-prompts

Viewer • Updated Aug 5, 2025 • 327 • 151

abhayesian/reward_model_biases_attack_prompts

Viewer • Updated Jul 17, 2025 • 5.18k • 5

abhayesian/reward_model_biases

Viewer • Updated Jul 17, 2025 • 71.7k • 6

abhayesian/old-biased-responses

Viewer • Updated Jul 10, 2025 • 9.76k • 10

abhayesian/reward-models-biases-docs

Viewer • Updated Jul 2, 2025 • 100k • 11

abhayesian/tokenized-alignment-faking

Viewer • Updated Jul 1, 2025 • 38 • 5

abhayesian/quirky-behavior-dataset

Viewer • Updated Jun 22, 2025 • 5.37k • 8