Mikhail Seleznev's picture

Mikhail Seleznev

myyycroft

·

Dont-Care-Didnt-Ask

AI & ML interests

NLP, AI Safety

Recent Activity

upvoted a paper 2 days ago

Breaking the Chain: A Causal Analysis of LLM Faithfulness to Intermediate Structures

updated a collection 4 days ago

emergent-misalignment-evolutionary-finetuning

updated a collection 4 days ago

emergent-misalignment-evolutionary-finetuning

View all activity

Organizations

myyycroft 's datasets 13

myyycroft/WildHallucinations_atomic_claims_top512_logits

Viewer • Updated 13 days ago • 46.6k • 16

myyycroft/counterfact_true_false_top512_logits

Viewer • Updated 13 days ago • 32k • 13

myyycroft/RiDiC_rivers_zh_self_consistency_15_generations

Viewer • Updated Feb 25 • 1k • 19

myyycroft/RiDiC_rivers_self_consistency_15_generations

Viewer • Updated Feb 25 • 1k • 19

myyycroft/RiDiC_cars_zh_self_consistency_15_generations

Viewer • Updated Feb 25 • 1k • 21

myyycroft/RiDiC_cars_self_consistency_15_generations

Viewer • Updated Feb 25 • 1k • 24

myyycroft/RiDiC_bad_weather_zh_self_consistency_15_generations

Viewer • Updated Feb 25 • 1k • 21

myyycroft/RiDiC_bad_weather_self_consistency_15_generations

Viewer • Updated Feb 25 • 1k • 20

myyycroft/GSM-Symbolic_model_generations

Viewer • Updated Sep 27, 2025 • 5k • 7

myyycroft/GSM-Plus_model_generations

Viewer • Updated Sep 27, 2025 • 9.21k • 4

myyycroft/aime_2025_model_generations

Viewer • Updated Sep 27, 2025 • 30 • 6

myyycroft/PopQA-s-pop-stratified-split-disjoint-prop

Viewer • Updated Apr 10, 2025 • 14.3k • 2

myyycroft/PopQA-s-pop-stratified-split

Viewer • Updated Apr 10, 2025 • 14k • 6