16 posts tagged with "llm"

How I quickly hot-swap my financial agent with different LLM providers - fully open source.

Ever wondered what it would be like to have an AI that writes exactly in your style? I did. And in this post, I share what I did about it. This is a very practical guide on how to fine-tune an LLM using LoRA with MLX on Apple Silicon.

This post explores Test-Driven AI Development, where AI writes its own tests and prompts, potentially making manual prompt engineering obsolete. It covers how self-improving AI systems can be built and the implications of this paradigm shift.

The financial industry's rush to adopt AI without proper data security is creating an 'OceanGate moment' - a disaster waiting to happen. This post explores the risks of reckless AI implementation and charts a safer path forward through on-premise and local model deployment.

In this blog post, I'll show you how an AI agent can transform your funds performance, macro data, news around your holding companies, and more into a draft investor letter that has the same writing style as your team.

Building on OpenBB's presentation at the Anote AI Day Summit, this post explores how intelligent function calling serves as the cornerstone of our AI-native workspace for data analytics.

A practical exploration of using Gemini's long context window capabilities to analyze multi-page documents, featuring a Streamlit app for testing and iterating prompts.

Learn how to move beyond traditional RAG approaches for document analysis and leverage the power of large context windows for more accurate information retrieval.

The open source code is available here.

This project converts blog feed content into a structured Question-Answer dataset using LLaMA 3.2 (via Ollama) for local processing. The generated dataset follows a conversational format and can be automatically pushed to Hugging Face.

The open source code is available here.

A practical guide to building an AI agent that processes Telegram messages through a local LLM, gathers context from various sources (OpenBB, Perplexity, Grok), and automatically posts content to Bluesky.

The open source code is available here.

I took the stage at the Cornell Quant Conference alongside Yu Yu (BlackRock) Tony Berkman (Two Sigma), and Samson Qian (Citadel), to discuss ChatGPT & The Future of AI in Finance.

AI will change education forever. Here's how I leveraged Perplexity, Cursor and ChatGPT to teach Supervised Learning and assess coursework.

The open source code is available here.

For the past few weeks, we’ve been working on the OpenBB Copilot, an ever-present financial analyst at your fingertips with the OpenBB Terminal Pro.

The SlackGPT is a Slack bot that summarizes conversations and sends you a summary per channel.

The open source code is available here.

Companies will own multiple fine-tuned LLMs/SLMs for specific tasks.

Our Platform aims to empower the OpenBB Copilot, an AI-powered financial analyst, to perform tasks ranging from knowledge retrieval to fully autonomous analysis. The architecture involves task decomposition, tool retrieval, and subtask agents, showcasing impressive results in both deterministic and non-deterministic workflows. Read on to explore its capabilities and don't forget to watch the demos.

The open source code is available here.

In this blog post, I share how I used the OpenAI API to improve our product documentation. I used ChatGPT to generate more detailed descriptions for our OpenBB Bot Discord commands, making them more understandable for new users.

The open source code is available here.