It’s been more than 3 years since the concept of a prompt injection was first popularized, and in that time AI has gone from “barely coherent conversations” to “autonomous discovery of novel vulnerabilities in the Linux kernel”. But models
It’s been more than 3 years since the concept of a prompt injection was first popularized, and in that time AI has gone from “barely coherent conversations” to “autonomous discovery of novel vulnerabilities in the Linux kernel”. But models
A popular assertion among cognitive psychologists is that large language models (LLMs) rely on a “developmentally implausible” form of language learning. There are many points of discordance between AI and human development, but data ineffi…
A lot of academic attention has been focused on the topic of adversarial attacks against neural networks recently, and for good reason. Because we still lack a thorough understanding of why neural networks work well, the failure modes of ne…