Bookmarks tagged llm

19 Apr hamel.dev
"Quickly understand inscrutable LLM frameworks by intercepting API calls."
26 Jan blog.partykit.io
"The tl;dr is that search got really good suddenly and really easy to build because of AI."
12 Dec 2023 arxiv.org
"Recent work claims that large language models display emergent abilities, abilities not present in smaller-scale models that are present in larger-scale models. What makes emergent abilities intriguing is two-fold: their sharpness, transitioning seemingly instantaneously from not present to present, and their unpredictability, appearing at seemingly unforeseeable model scales. Here, we present an alternative explanation for emergent abilities: that for a particular task and model family, when analyzing fixed model outputs, emergent abilities appear due to the researcher's choice of metric rather than due to fundamental changes in model behavior with scale"
20 Nov 2023 metaflow.org
"Open-source Metaflow makes it quick and easy to build and manage real-life data science and ML projects. "
19 Nov 2023 simonwillison.net
"Embeddings are based around one trick: take a piece of content—in this case a blog entry—and turn that piece of content into an array of floating point numbers."
19 Nov 2023 www.understandingai.org
"We’ll start by explaining word vectors, the surprising way language models represent and reason about language. Then we’ll dive deep into the transformer, the basic building block for systems like ChatGPT. Finally, we’ll explain how these models are trained and explore why good performance requires such phenomenally large quantities of data."
14 Nov 2023 www.businessinsider.com
"The scientists had used ChatGPT 3.5 to build the bots for a very specific purpose: to study how to create a better social network — a less polarized, less caustic bath of assholery than our current platforms. They had created a model of a social network in a lab — a Twitter in a bottle, as it were — in the hopes of learning how to create a better Twitter in the real world. "Is there a way to promote interaction across the partisan divide without driving toxicity and incivility?" wondered Petter Törnberg, the computer scientist who led the experiment. "