Numbers Every LLM Developer Should Know
tl;dr: (1) 40 -90% is the Amount saved by appending “be concise” to your prompt. (2) 1.3:1 is the average tokens per word. (3) ~50:1 is the cost ratio of GPT-4 to 3.5. And more.featured in #415
Inside GitHub: Working With The LLMs Behind GitHub Copilot
- Sara Verdi tl;dr: “Due to the growing interest in LLMs and generative AI models, we decided to speak to the researchers and engineers at GitHub who helped build the early versions of GitHub Copilot and talk through what it was like to work with different LLMs from OpenAI, and how model improvements have helped evolve GitHub Copilot to where it is today—and beyond.”featured in #415
RLHF: Reinforcement Learning From Human Feedback
- Chip Huyen tl;dr: How exactly does RLHF work? Why does it work?” Chip discusses the answers to these questions. “RL has been notoriously difficult to work with, and therefore, mostly confined to gaming and simulated environments. Just five years ago, both RL and NLP were progressing pretty much orthogonally – different stacks, different techniques, and different experimentation setups. It’s impressive to see it work in a new domain at a massive scale.”featured in #414
50+ ChatGPT Prompts For Web Developers
tl;dr: "In this blog post, we'll provide you with over 50 prompts and strategies that will help you speed up your web development workflow using ChatGPT. From learning concepts as a beginner to preparing for interviews."featured in #413
The Future Of Programming: Research At CHI 2023
- Austin Henley tl;dr: “The esteemed CHI conference is happening this week, and I'm jealous that I can't be there. Instead, I'm going through the proceedings and reading all of the papers related to programming, of which many involve AI.”featured in #410
Prompt Engineering Vs Blind Prompting
- Mitchell Hashimoto tl;dr: “In this blog post, I will make the argument that prompt engineering is a real skill that can be developed based on real experimental methodologies. I will use a realistic example to walk through the process of prompt engineering a solution to a problem that provides practical value to an application.”featured in #408
Semantic Search In iMessage, iMessage Wrapped, And AI Conversations
- JonLuca DeCaro tl;dr: “I realized that iMessage just stores its database locally as a sqlite file, so I went about building an alternate UI for searching, and adding in a few features that I thought would be interesting. These include: (1) Semantic Search (2) Wrapped: stats about my life on iMessage (2) AI conversations with friends. And more.featured in #406
GitHub Copilot X: The AI-Powered Developer Experience
- Thomas Dohmke tl;dr: GitHub Copilot is evolving into an AI assistant, introducing chat and voice for Copilot, and bringing Copilot to pull requests, the command line, and docs to answer questions on your projects. Thomas illustrates how that will work.featured in #400
No-Code Has No Future In A World Of AI
- Ravi Parikh tl;dr: Ravi Parikh, CEO of Airplane, discusses how AI-driven software development will dwarf no-code tools' capabilities and eventually make no-code obsolete.featured in #394
Let's Build GPT: From Scratch, In Code, Spelled Out
- Andrej Karpathy tl;dr: "We build a GPT, following the paper "Attention is All You Need" and OpenAI's GPT-2 / GPT-3. We talk about connections to ChatGPT, which has taken the world by storm. We watch GitHub Copilot, itself a GPT, help us write a GPT."featured in #382