A software engineer compares the hype around cryptocurrencies and LLMs, arguing that LLMs provide tangible value while crypto is plagued by scams.
A developer shares experiments building LLM-powered tools for research, reflection, and planning, including URL summarizers, SQL agents, and advisory boards.
Explores autoregressive models, their relationship to joint distributions, and how they handle out-of-distribution prompts, with insights relevant to LLMs.
Explores using GPT-3 text embeddings and a simple classifier to predict the winner of a headline A/B test, potentially replacing traditional testing.
Explores the Reflexion technique where LLMs like GPT-4 can critique and self-correct their own outputs, a potential new tool in prompt engineering.
A reflection on past skepticism of deep learning and why similar dismissal of Large Language Models (LLMs) might be a mistake.
An experiment comparing how different large language models (GPT-4, Claude, Cohere) write a biography, analyzing their accuracy and training data.
An overview of prompt engineering techniques for large language models, including zero-shot and few-shot learning methods.
A tutorial on coding self-attention, multi-head attention, causal attention, and cross-attention in LLMs using Python and PyTorch.
An overview of four different methods for detecting AI-generated text, including OpenAI's AI Classifier, DetectGPT, GPTZero, and watermarking.
