Lukas Galke Poech

lgalke

·

https://lgalke.github.io

AI & ML interests

LLM interpretability, agentic/multi-agent safety

Recent Activity

upvoted a paper about 1 hour ago

DFM Mimir v1: An Open HRM Delivering Frontier Performance at 1B Parameters Using Only Permissible Post-Training Data

authored a paper 2 months ago

The Arbiter Agent: Continually Monitoring Multi-Agent Conversations to Detect Emergent Misalignment

upvoted a paper 2 months ago

The Arbiter Agent: Continually Monitoring Multi-Agent Conversations to Detect Emergent Misalignment

View all activity

Organizations

lgalke 's datasets

None public yet