LLM - CybAI news

14 Nov

AI Agent Systems: Modular Engineering for Reliable Enterprise AI Applications

stp2y0 CommentsViral NewsAgent, GenAI, generative ai, LLM, rag

Monolithic to ModularThe proof of concept (POC) of any new technology often starts with large, monolithic units that are difficult to characterize. By definition, POCs are designed to show that a technology works without considering issues around extensibility, maintenance, and quality. However, once technologies achieve maturity and are deployed widely, these needs drive product development to be broken down into smaller, more manageable units. This is the fundamental concept behind systems thinking and why we are seeing AI implementation move from models to AI agent systems. The concept of modular design has been applied to:Cars: seats, tires, lights, and engines can…

23 Oct

How Ragie Outperformed the FinanceBench Test

stp2y0 CommentsNewsai, coding, community, development, engineering, inclusive, LLM, rag, showdev, software

In this article, we’ll walk you through how Ragie handled the ingestion of over 50,000+ pages in the FinanceBench dataset (360 PDF files, each roughly 150-250 pages long) in just 4 hours and outperformed the benchmarks in key areas like the Shared Store configuration, where we beat the benchmark by 42%. For those unfamiliar, the FinanceBench is a rigorous benchmark designed to evaluate RAG systems using real-world financial documents, such as 10-K filings and earnings reports from public companies. These documents are dense, often spanning hundreds of pages, and include a mixture of structured data like tables and charts with…

21 Oct

How to use Llama3.2 to write daily logs in Notion based on your screen

stp2y0 CommentsNewsai, coding, community, development, engineering, inclusive, javascript, LLM, productivity, software

Ever wished you had a personal AI assistant that could keep track of your daily work? With screenpipe & llama3.2, you can now automate the process of writing detailed logs based on your screen activity. Let's dive into how you can set this up using screenpipe's plugin system. What is screenpipe? screenpipe is an open-source tool that captures your screen and audio 24/7, extracts text using ocr, and allows you to build personalized ai-powered workflows. It's designed to be secure, with your data staying on your machine. Installing screenpipe (If you're not on macOS check these instructions) To build the…

17 Oct

How to Consistently Retrieve Valid JSON from Claude 3.5 in Go

stp2y0 CommentsNewsai, chatgpt, coding, community, development, engineering, go, inclusive, LLM, software

When working with LLMs as a developer, you often want to receive data in a structured format. While this didn't always work well in the early GPT-3 era, the current models that support function calling are much better at it. In this post, I want to share a simple function called CallClaudeForceTool, which you can use to call Claude to receive structured data/JSON output. In my case, it is written in Golang and returns any type of struct I need. First, you need to define the structure and provide it to the LLM in the format of a JSON schema.…

20 Sep

Fine-tuning Llama 3.1 with Long Sequences

stp2y0 CommentsViral Newsfinetuning, GenAI, generative ai, LLM

We are excited to announce that Mosaic AI Model Training now supports the full context length of 131K tokens when fine-tuning the Meta Llama 3.1 model family. With this new capability, Databricks customers can build even higher-quality Retrieval Augmented Generation (RAG) or tool use systems by using long context length enterprise data to create specialized models.The size of an LLM’s input prompt is determined by its context length. Our customers are often limited by short context lengths, especially in use cases like RAG and multi-document analysis. Meta Llama 3.1 models have a long context length of 131K tokens. For comparison,…

16 Sep

DialectMorph – A CLI Tool To Transpile Code

stp2y0 CommentsNewscli, coding, community, development, engineering, inclusive, LLM, opensource, software, typescript

Introduction The idea for DialectMorph came to me when I initially tried to encapsulate a function for making an API call in an object using TypeScript. However, I later discovered that the API only supported Python, so I had to use AI agents to help me transpile the code from TypeScript to Python. This challenge inspired me to create a CLI tool that would simplify this process, essentially acting as a CLI wrapper for AI-driven code transpilation, which led to the development of DialectMorph. Tech Stack Used The entire project is based on TypeScript with different libraries that support the…

11 Sep

Key differences in GPT3.5 VS GPT4.0

stp2y0 CommentsNewschatgpt, coding, community, development, engineering, GenAI, inclusive, LLM, software

GPT-3.5 and GPT-4 are both large language models developed by OpenAI, but they differ in several key areas: Size and Architecture: GPT-3.5: Has 175 billion parameters and a transformer architecture. GPT-4: Is significantly larger and more complex, with an estimated 1 trillion parameters and a more advanced transformer architecture. Capabilities: Text Generation: Both models are excellent at generating human-quality text, but GPT-4 is generally more creative and able to produce more diverse and nuanced responses. According to OpenAI, ChatGPT-4 is “82 percent less likely to respond to requests for disallowed content and 40 percent more likely to produce factual responses…

28 Aug

How to Evaluate Jailbreak Methods: A Case Study with the StrongREJECT Benchmark

stp2y0 CommentsAIai, AI safety, jailbreak, LLM

When we began studying jailbreak evaluations, we found a fascinating paper claiming that you could jailbreak frontier LLMs simply by translating forbidden prompts into obscure languages. Excited by this result, we attempted to reproduce it and found something unexpected. (more…)

03 Aug

Build your own AI Video editor with Node.js, AssemblyAI & StreamPot (hosted)

stp2y0 CommentsNewsai, coding, community, development, engineering, inclusive, javascript, LLM, node, software

Note: this is a revised version of this article, using the new hosted StreamPot You may have seen AI startups that magically turn long podcast videos into viral clips for TikTok. To do this they use a Large Language Model (LLM), like GPT-4, to find the best bits. In this guide, you’ll learn how to build your own AI video editor. You will: Use AssemblyAI to transcribe and generate video highlights. Use StreamPot to extract audio and make clips. Here is a repo with the final code By the time you finish, you’ll be producing your own AI generated video…

30 Jul

LangGraph.js Concept Guide

stp2y0 CommentsNewschatgpt, coding, community, development, engineering, inclusive, langchain, LLM, openai, software

Welcome to LangGraph.js, a JavaScript library designed for building complex, scalable AI agents using a graph-based state machine. In this guide, we will explore the core concepts behind LangGraph.js and why it excels in creating reliable and fault-tolerant agent systems. We assume you have already learned the basics introduced in the Quick Start guide and want to dive deeper into the fundamental design and internal workings of LangGraph.js. Background: Agents as Graphs and AI Workflows While definitions of "AI agents" vary, we define an "agent" as any system that allows a language model to control looped workflows and take actions.…