Chris O'Quinn

Introduction Deep Learning has come to be associated with a general rule: Bigger Is Better. For tasks such as image or text processing, this has seemed to pan out: more parameters has almost always produced more capacity. In the domain I work in, Natural Language Processing (NLP), we use Large...

I'm a machine learning researcher who has been working in AI alignment and safety. I'm sharing this because I believe I've identified some fundamental gaps in our current approach to AI safety that warrant serious discussion. Over the past year, I've been conducting safety wargaming exercises—essentially red-teaming our alignment assumptions...