meemi

For years I had a blindspot in my thinking. I dismissed policy and advocacy work as “in another [lower-status] category” because I’m obviously a technical person![1] Even when I felt super pessimistic about my ability to do research that meaningfully contributes to addressing the threat of extinction from AI. I’m...

Summary We study language models' capability to perform parallel reasoning in one forward pass. To do so, we test GPT-3.5's ability to solve (in one token position) one or two instances of algorithmic problems. We consider three different problems: repeatedly iterating a given function, evaluating a mathematical expression, and calculating...