Specification gaming is a behaviour that satisfies the literal specification of an objective without achieving the intended outcome. (more…)
Read more »
Ask your terminal (AI) about cli commands. Contribute to kynnyhsap/how development by creating an account on GitHub. (more…)
Read more »
We consider the paradigm of a black box AI system that makes life-critical
decisions. We propose an "arguing machines" framework that pairs the primary AI
system with a secondary one that is independently trained to perform the same
task. We show that dis... (more…)
Read more »