The limitations of LLMs, or why are we doing RAG?
Explains the limitations of Large Language Models (LLMs) and introduces Retrieval Augmented Generation (RAG) as a solution for incorporating proprietary data.
Explains the limitations of Large Language Models (LLMs) and introduces Retrieval Augmented Generation (RAG) as a solution for incorporating proprietary data.
Sample code and review of the new official OpenAI SDK for .NET, including chat, audio, and image analysis demos.
A software engineer reflects on his blogging hiatus, the impact of AI on writing, and his renewed motivation to create authentic human content.
A developer's experience using ChatGPT 4 as a tool for exploring and learning new technical concepts, from programming to machine learning.
Tutorial on building an AI-powered expense tracker app using SwiftUI, integrating Firestore and ChatGPT, for iOS, macOS, and visionOS.
A backend developer shares a hackathon experience using ChatGPT for frontend coding, highlighting its limitations and the need for domain expertise.
Explores the balanced use of AI coding tools like GitHub Copilot, discussing benefits, risks of hallucinations, and best practices for developers.
An Atlantic article explores how Google's AI-generated Quick Answers, sourced from sites like Emergent Mind, are spreading misinformation.
An analysis of ChatGPT's knowledge cutoff date, testing its accuracy on celebrity death dates to understand the limits of its training data.
Discusses OpenAI's API restrictions for wrapper apps, SpriteKit game development updates, and migrating a website from WordPress to Astro.
A developer documents building a game-playing AI using ChatGPT and Ruby on Rails, covering API integration, token management, and frontend development.
A developer explores building a resilient, Rails-based system to integrate ChatGPT for playing video games, inspired by a Twitch streamer's Python script.
A developer's notes on Cory Zue's Django livecoding session, comparing Django's ORM, migrations, and admin UI to Flask development.
Explains Retrieval Augmented Generation (RAG) for using ChatGPT with custom data, including a C# implementation sample.
A developer documents their experiment using ChatGPT to build a full-stack web application, detailing the tech stack, challenges, and outcomes.
An analysis of ChatGPT's future, predicting challenges like company dilution, failed competition, and a potential acquisition.
A native macOS app providing quick menu bar, Dock, and keyboard shortcut access to ChatGPT, with FAQs on features and limitations.
A developer compares GPT-4 to GPT-3.5, sharing hands-on experiences with coding tasks and evaluating the AI's strengths and weaknesses.
The author discusses the current state and future potential of AI in software development, focusing on bug fixing, documentation, and the need for developers to stay sharp.
Argues against the 'lossy compression' analogy for LLMs like ChatGPT, proposing instead that they are simulators creating temporary simulacra.