Sublime
An inspiration engine for ideas
Arvin Leeuwis
arvinleeuwis.com
Inspired by @AndrewYNg’s threads on agents in the past few weeks, I’m excited to share my talk from the @weights_biases conference that outlines how to build a general context-augmented research assistant 🧑🔬
Naive RAG is mostly good for simple questions in a single-shot setting. But building a research agent enables ... See more
Tyler Angert
tyler.cafe
Blown by @GregKamradt's LangChain playlist on YT.
Not for how it introduces LangChain, but especially for the ideas and fresh use of LLMs for common NLP tasks.
Here's my 3 favourite:
Leonardo Schettinix.comWill we hire engineers in the future?
Prompting is thinking. The sharper your thoughts, the better the prompts, the better the outputs. Engineering and design are headed into a world where most of the output is produced by prompting, if not all.
The way we interview engineers has already bee... See more
Guillermo Rauchx.comStefan Sohlstrom
stefansohlstrom.comFor trying to understanding LMs deeply, @AiEleuther’s Pythia has been an invaluable resource: 16 LMs (70M to 12B parameters) trained on the same data (The Pile) in the same order, with intermediate checkpoints. It’s been two years and it’s time for a refresh.
Percy Liangx.comKarl Yang
karlyang.net
People are realizing RLHF can be easy with DPO and SLiC-HF. If you were wondering how they compare, the answer is they are pretty similar and our paper (https://t.co/D8bASJumi8... See more