Argues that building a good search engine is more critical for effective RAG than just using a vector database, as poor retrieval misleads AI.
Analyzes why building Large Language Models (LLMs) may be a poor business, comparing the AI industry's structure to historically unprofitable sectors like airlines.
Explores a method using a 'Judging AI' (like o1-preview) to evaluate the performance of other AI models on tasks, relative to human capability.
Autoshow is a tool for automating content repurposing, including transcription, summarization, and chapter generation from audio/video.
Explores the use of LLMs to generate synthetic data for training AI models, discussing challenges, an experiment with coding data, and a new library.
The article explores how the writing process of AI models can inspire humans to overcome writer's block by adopting a less perfectionist approach.
Explores the philosophical argument that AI, particularly LLMs, possess a form of understanding and model reality, challenging the notion they are mere token predictors.
A guide to transforming pretrained LLMs into text classifiers, with insights from the author's new book on building LLMs from scratch.
Building a multi-service document extraction app using LLMs, Azure services, and Diagrid Catalyst for cloud-native architecture.
A 3-hour coding workshop teaching how to implement, train, and use Large Language Models (LLMs) from scratch with practical examples.
A 3-hour coding workshop video covering the implementation, training, and use of Large Language Models (LLMs) from scratch.
A philosophical and technical exploration of how Large Language Models (LLMs) transform 'next token prediction' into meaningful answer generation.
A hands-on review of K8sGPT, an AI-powered CLI tool for analyzing and troubleshooting Kubernetes clusters, including setup with local LLMs.
Analyzes the latest pre-training and post-training methodologies used in state-of-the-art LLMs like Qwen 2, Apple's models, Gemma 2, and Llama 3.1.
A technical review of the latest pre-training and post-training methodologies used in state-of-the-art large language models (LLMs) like Qwen 2 and Llama 3.1.
A developer creates a Bash script called 'qq' to query Kagi's FastGPT API from the terminal, improving on a command-line LLM tool concept.
A tutorial on building a ChatGPT-like chat application using Ruby on Rails and the Claude 3.5 Sonnet AI model, covering setup, models, and integration.
Analyzing if a Codenames bot can win using only card layout patterns, without understanding word meanings.
Explores how AI can revolutionize communication by bridging context gaps between people, using tools like RAG and AI assistants as proxies.
A satirical web app uses LLMs to roast GitHub profiles, highlighting a Svelte-based implementation and straightforward API.
