William Brach

williambrach

9 1

·

AI & ML interests

nlp, web scraping, web crawl, language models, benchmarks

Recent Activity

upvoted a paper 25 days ago

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

upvoted a paper about 1 month ago

LLMs Can Leak Training Data But Do They Want To? A Propensity-Aware Evaluation of Memorization in LLMs

authored a paper about 1 month ago

Emergent Languages in Populations of Language Model Agents: From Token Efficiency to Oversight Evasion

View all activity

Organizations

williambrach 's models

None public yet