Program of Thoughts 

The Evolution of Numerical Reasoning in AI: The Power of Program of Thoughts (PoT) This article is based on the paper Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks by Wenhu Chen and others. Author Introduction Artificial Intelligence has made significant strides in solving complex numerical reasoning tasks. Traditional approaches focused […]

From Hallucination to Verification: Making AI Responses More Trustworthy

How Chain-of-Verification Creates More Reliable AI Systems This article explores and analyses the paper ‘Chain-of-Verification Reduces Hallucination in Large Language Models‘ by Shehzaad Dhuliawala and colleagues from Meta AI & ETH Zürich. The paper was published on arXiv in September 2023. Author Introduction As Large Language Models (LLMs) become increasingly integrated into our digital infrastructure, […]

Contrastive Chain of Thought

Enhancing LLMs to Think Like Humans This article is based on the paper Contrastive Chain-of-Thought Prompting by Yew Ken Chia and others. Introduction In recent years, Large Language Models (LLMs) have demonstrated remarkable performance across a variety of natural language processing tasks. However, their ability to perform complex reasoning remains a key challenge. Unlike humans, […]

The Ultimate FLUX.1 Hands-On Guide

Learn to Use FLUX.1: The Unlimited Image Generator Behind Elon Musk’s Grok 2 Author Introduction In this article, we will guide you step-by-step on how to use FLUX.1. The open-source community has welcomed a new text-to-image generation model, FLUX.1, following the releases of SD 3 Medium and Kolors. Developed by former core members of Stability […]

Llama 3.1 405B vs GPT-4o: Which model is better?

Evaluating Llama 3.1–405B and GPT-4o Across Key Performance Metrics to Determine the Superior AI Model for Users and Developers. Author Introduction To compare the strengths and intelligence of Llama-3.1–405B and GPT-4o from a practical usage perspective, this article designed test cases covering five scenarios: mathematics, coding, tool usage, JSON extraction, and creative writing. We conducted […]

How to use Flowise locally

A Comprehensive Guide Introduction Flowise is an open-source, low-code tool tailored for developers to build customised orchestration flows and AI agents for Large Language Models (LLMs). It simplifies the development cycle, enabling quick iterations and a smooth transition from testing to production. In this article, we will explore the primary use cases for Flowise. Get […]

What is Phi-3.5-vision?

Explained with Working Examples Introduction The field of artificial intelligence has taken another significant leap forward with the introduction of Phi-3.5-vision, a cutting-edge multimodal AI model developed by Microsoft. This lightweight yet powerful model represents a new frontier in machine learning, combining advanced natural language processing capabilities with sophisticated image understanding. Phi-3.5-vision stands out for […]

Automated Knowledge Graph Construction with Large Language Models

Harvesting the Power and Knowledge of Large Language Models Author Introduction Knowledge Graphs are networks that represent data in a graphical format. The beauty of Knowledge Graphs lies in their representation of concepts, events and entities as nodes, and the relationships between them as edges. These relationships determine the context of the node, and consequently, allow for […]