A review of key trends and developments in Large Language Models (LLMs) throughout 2025, focusing on reasoning models, agents, and industry shifts.
OpenAI has rebranded its Codex Cloud service to Codex Web, aligning the name with its web application interface.
OpenAI releases GPT-5.2-Codex, a model optimized for agentic coding with improvements in refactoring, Windows performance, and cybersecurity.
OpenAI's ChatGPT Images update focuses on faster generation, better instruction following, and lower costs, with comparisons to competitor models.
OpenAI is quietly adding 'skills' support to ChatGPT and Codex CLI, a feature inspired by Anthropic for extending AI capabilities with custom folders and scripts.
OpenAI announces GPT-5.2, a major AI model update with new variants, improved benchmarks, and advanced features like response compaction.
A retrospective on ChatGPT's third anniversary, covering its surprising launch, initial internal skepticism, and unprecedented growth to 800 million users.
OpenAI releases GPT-5.1 API with new reasoning modes, adaptive reasoning, extended prompt caching, and new built-in tools for developers.
OpenAI objects to court order demanding 20M ChatGPT user conversations, citing dangerous precedent for AI discovery.
A developer reverse-engineers the Codex CLI to directly prompt the new GPT-5-Codex-Mini model, detailing the process in a technical blog post.
Analysis of OpenAI's 2025 recapitalization into a public benefit corporation, Microsoft's $135B stake, and the governance structure for AGI development.
A live coding session demonstrating the rapid development of 'Arena', a feature for analyzing user compatibility via Twitter/X data, using AI-assisted tools.
Analyzes the architectural advancements in OpenAI's new open-weight gpt-oss models, comparing them to GPT-2 and other modern LLMs.
An analysis of key AI trends in 2025, focusing on industry leaders, AGI debates, and AI's impact on software development and science.
A tutorial on building a full-stack React.js AI chat app using the AI SDK to simplify streaming and state management.
Explores the latest developments in using reinforcement learning to improve reasoning capabilities in large language models (LLMs).
A tutorial on building a command-line chatbot using Node.js, LangChain, and OpenAI's API for interactive conversations.
Learn how to accurately calculate token counts for strings using language models with a provided Jupyter Notebook tool.
A guide on using Anthropic's Model Context Protocol (MCP) to connect AI agents with tools and data sources using various LLMs like OpenAI or Gemini.
