In-context learning (ICL) is now a common method for teaching large language models (LLMs) new tasks: given labeled examples in the input context, the LLM learns to perform the task without weight updates. Do models guided via ICL infer the underlying structure of the task defined by the context, or do they rely on superficial heuristics that only generalize to identically distributed examples? We address this question using transformations tasks and an NLI task that assess sensitivity to syntax - a requirement for robust language understanding. We further investigate whether out-of-distribution generalization can be improved via chain-of-thought prompting, where the model is provided with a sequence of intermediate computation steps that illustrate how the task ought to be performed. In experiments with models from the GPT, PaLM, and Llama 2 families, we find large variance across LMs. The variance is explained more by the composition of the pre-training corpus and supervision methods than by model size; in particular, models pre-trained on code generalize better, and benefit more from chain-of-thought prompting.

China claims to have built the "world's largest quadruped bionic robot," a gigantic "mechanical yak" that can carry over 350 pounds at a shambling 6.2 mph, according to a report by the state-run Global Times. The goal is to carry gear for soldiers stationed in remote areas. A clip shared by the People's Daily, also associated with the Chinese government, shows a behemoth-sized quadruped going for a stroll along an empty road. It can also be seen tackling dusty inclines in the desert, an impressive mechanical feat that could one day be of huge benefit in areas inaccessible to conventional vehicles, and even weaponized. China's first domestically built "yak" robot with a load capacity of 160 kg made its debut recently.

This study investigates the public health intelligence utility of Yik Yak, a social media platform that allows users to anonymously post and view messages within precise geographic locations. Our dataset contains 122,179 “yaks” collected from 120 college campuses across the United States during 2015. We first present an exploratory analysis of the topics commonly discussed in Yik Yak, clarifying the health issues for which this may serve as a source of information. We then present an in-depth content analysis of data describing substance use, an important public health issue that is not often discussed in public social media, but commonly discussed on Yik Yak under the cloak of anonymity.