YANG SHU
babytreecc
AI & ML interests
None yet
Recent Activity
authored
a paper
18 days ago
When Thinking Backfires: Mechanistic Insights Into Reasoning-Induced
Misalignment
upvoted
a
paper
18 days ago
When Thinking Backfires: Mechanistic Insights Into Reasoning-Induced
Misalignment
updated
a dataset
25 days ago
babytreecc/DeliberationBank