Our team has deployed industrial AI agents across various domains. We’re now applying sparse autoencoders to better understand the internals of LLMs and ensure our agents stay safe and aligned. Excited to chat about agents, evals, and SAEs - and by the way, we are hiring!
Our team has deployed industrial AI agents across various domains. We’re now applying sparse autoencoders to better understand the internals of LLMs and ensure our agents stay safe and aligned. Excited to chat about agents, evals, and SAEs - and by the way, we are hiring!