🔗 Links of the week: AI, GPT, Prompt Engineering

OpenAI API: If you want to call OpenAI’s models (e.g. ChatGPT) programmatically or build AI-based products.

Neural Networks: Zero to Hero: If you want to understand how GPT works from the ground up (I’ve only watched the first two videos but they’ve been fantastic).

A simple Python implementation of the ReAct pattern for LLMs: How a simple plugin system works.

Prompt injection: What’s the worst that can happen?: The most serious vulnerability of GPT-based applications.

The Dual LLM pattern for building AI assistants that can resist prompt injection: A proposal to fix this vulnerability.

Prompt Engineering vs. Blind Prompting: Prompt Engineering in a nutshell (is it real engineering or is it just hype, how to do it well).

Prompt Engineering: Prompt Engineering in detail.

Web LLM runs the vicuna-7b Large Language Model entirely in your browser, and it’s very impressive: A very small LLM that gives surprisingly good results.