alex.lloyd hasn't written anything yet.
alex.lloyd has not written any posts yet.
Summary Zurich AI Safety (ZAIS) is hiring a Director, with the goal of professionalizing AI Safety capacity building in Zurich and Switzerland. The Director will lead individualized career advising for promising talent, expand outreach to mid- and senior-level professionals, manage ZAIS's growing volunteer team, and explore AI Safety opportunities in...
Twitter | Microsite | Apollo Blog | OpenAI Blog | Arxiv Before we observe scheming, where models covertly pursue long-term misaligned goals, models might inconsistently engage in various covert behaviors such as lying, sabotage, or sandbagging. This can happen for goals we give to models or they infer from context,...
TL;DR: Zurich AI Safety (ZAIS) is looking for a Director or Co-Directors. As of now, ZAIS is purely volunteer-run and is applying for funding for this position in collaboration with EA Switzerland. Therefore, this is an expression of interest (EOI) rather than a secured hiring, but promising candidates will be...