Models
ChatGPT users revolt over GPT-5 release — OpenAI battles claims that the new model’s accuracy and abilities fall short
OpenAI made a controversial move at the end of last week by replacing all of its older GPT-4 models with a single GPT-5 model, which it claimed was more accurate, more capable, and faster than ever before. Although some users have highlighted its impressive response times and ability to pass certain technical tests, users have…
The Best Chinese Open Agentic/Reasoning Models (2025): Expanded Review, Comparative Insights & Use Cases
China continues to set the pace in open-source large-language-model innovation, especially for agentic architectures and deep reasoning. Here is a comprehensive, up-to-date guide to the best Chinese open agentic/reasoning models, expanded with the newest and most influential entrants. 1. Kimi K2 (Moonshot AI) Profile: Mixture-of-Experts architecture, up to 128K context,…
OpenAI launches two ‘open’ AI reasoning models | TechCrunch
OpenAI announced Tuesday the launch of two open-weight AI reasoning models with similar capabilities to its o-series. Both are freely available to download from the online developer platform Hugging Face, the company said, describing the models as “state of the art” when measured across several benchmarks for comparing open models. The models come in two…
Small world: The revitalization of small AI models for cybersecurity
The last few months and years have seen a wave of AI integration across multiple sectors, driven by new technology and global enthusiasm. There are copilots, summarization models, code assistants, and chatbots at every level of an organization, from engineering to HR. The impact of these models is not only professional, but personal: enhancing our…
How to Use the SHAP-IQ Package to Uncover and Visualize Feature Interactions in Machine Learning Models Using Shapley Interaction Indices (SII)
In this tutorial, we explore how to use the SHAP-IQ package to uncover and visualize feature interactions in machine learning models using Shapley Interaction Indices (SII), building on the foundation of traditional Shapley values. Shapley values are great for explaining individual feature contributions in AI models but fail to capture feature interactions. Shapley interactions go…
A Coding Guide to Build an Intelligent Conversational AI Agent with Agent Memory Using Cognee and Free Hugging Face Models
In this tutorial, we delve into building an advanced AI agent with agent memory using Cognee and Hugging Face models, utilizing entirely free, open-source tools that work seamlessly in Google Colab and other notebook. We configure Cognee for memory storage and retrieval, integrate a lightweight conversational model for generating responses, and bring it all together…
Meet SmallThinker: A Family of Efficient Large Language Models LLMs Natively Trained for Local Deployment
The generative AI landscape is dominated by massive language models, often designed for the vast capacities of cloud data centers. These models, while powerful, make it difficult or impossible for everyday users to deploy advanced AI privately and efficiently on local devices like laptops, smartphones, or embedded systems. Instead of compressing cloud-scale models for the…
Implementing Self-Refine Technique Using Large Language Models LLMs
This tutorial demonstrates how to implement the Self-Refine technique using Large Language Models (LLMs) with Mirascope, a powerful framework for building structured prompt workflows. Self-Refine is a prompt engineering strategy where the model evaluates its own output, generates feedback, and iteratively improves its response based on that feedback. This refinement loop can be repeated multiple…
The unique, mathematical shortcuts language models use to predict dynamic scenarios
Let’s say you’re reading a story, or playing a game of chess. You may not have noticed, but each step of the way, your mind kept track of how the situation (or “state of the world”) was changing. You can imagine this as a sort of sequence of events list, which we use to update…
REST: A Stress-Testing Framework for Evaluating Multi-Problem Reasoning in Large Reasoning Models
Large Reasoning Models (LRMs) have rapidly advanced, exhibiting impressive performance in complex problem-solving tasks across domains like mathematics, coding, and scientific reasoning. However, current evaluation approaches primarily focus on single-question testing, which reveals significant limitations. This article introduces REST (Reasoning Evaluation through Simultaneous Testing) — a novel multi-problem stress-testing framework designed to push LRMs beyond isolated problem-solving…