Learn about how to prompt Command R: Understand the structured prompts used for RAG, formatting chat history and tool outputs, and changing sections of the prompt for different tasks.
Simon Willison recently delivered a talk during the Mastering LLMs: A Conference For Developers & Data Scientists, which was a six-week long online event. The talk centered around Simon's LLM Python command-line utility and its plugins, emphasizing how they can be utilized to explore Large Language Models (LLMs) and perform various tasks. Last week, he discussed accessing LLMs from the command-line, sharing valuable insights and techniques with the audience.
An analysis of Large Language Models' (LLMs) vulnerability to prompt injection attacks and potential risks when used in adversarial situations, like on the Internet. The author notes that, similar to the old phone system, LLMs are vulnerable to prompt injection attacks and other security risks due to the intertwining of data and control paths.
A CLI tool for interacting with local or remote LLMs to retrieve information about files, execute queries, and perform other tasks in a Retrieval-Augmented Generation (RAG) fashion.
LlamaIndex comes with a built-in indexing feature, which allows developers to index large datasets efficiently. This makes it easier to search and retrieve information from these datasets, ultimately improving the overall performance of LLM-based applications.
This post highlights how the GitHub Copilot Chat VS Code Extension was vulnerable to data exfiltration via prompt injection when analyzing untrusted source code.
A mixture of reflections, literature reviews and an experiment on Automated Prompt Engineering for Large Language Models
This article discusses how to overcome limitations of retrieval-augmented generation (RAG) models by creating an AI assistant using advanced SQL vector queries. The author uses tools such as MyScaleDB, OpenAI, LangChain, Hugging Face and the HackerNews API to develop an application that enhances the accuracy and efficiency of data retrieval process.
Retrochat is chat application that supports Llama.cpp, Kobold.cpp, and Ollama. It highlights new features, commands for configuration, chat management, and models, and provides a download link for the release.
Inspectus is a versatile visualization tool for large language models, offering multiple views to provide diverse insights into language model behaviors. It runs in Jupyter notebooks via a Python API and supports visualization of attention maps, token heatmaps, and dimension heatmaps. The library can be installed using pip and provides API documentation and tutorials for Huggingface models and custom attention maps.
