seojinlee
sjlee311
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 21 hours ago
The Devil Behind Moltbook: Anthropic Safety is Always Vanishing in Self-Evolving AI Societies
upvoted
a
paper
about 21 hours ago
Less is Enough: Synthesizing Diverse Data in Feature Space of LLMs
upvoted
a
paper
about 1 month ago
Can LLMs Predict Their Own Failures? Self-Awareness via Internal Circuits
Organizations
None yet