OpenAI released GPT-5.1, enhancing speed and efficiency for coding and agentic tasks. The model adapts its reasoning based on task complexity and introduces new tools like `apply_patch` for code editing and a shell tool for command execution. Developers can leverage extended prompt caching and a "no reasoning" mode for faster responses.

MiniMax-M2.5 is a large language model that enhances productivity in digital work environments, focusing on tasks like coding and office applications. It boasts improved efficiency and performance metrics compared to its predecessor, M2.1. The article also details various API relay service providers with discounts for users.

Anthropic has released Opus 4.5, improving conversation continuity in its Claude models by summarizing earlier dialogue instead of abruptly ending chats. The new model also achieves an 80.9% accuracy score, surpassing OpenAI's GPT-5.1 in coding tasks, though it still trails in visual reasoning.

This article provides guidance on optimizing the Codex model for coding tasks using the API. It covers recommended practices for prompting, tool usage, and code implementation to enhance performance and ensure efficient task completion.

Mistral has released Vibe 2.0, enhancing its terminal-native coding agent with new features like custom subagents, multi-choice clarifications, and slash-command skills. The update aims to streamline coding workflows and is available on Le Chat Pro and Team plans, with Devstral 2 now requiring paid API access.

The author shares insights from creating a unified coding agent harness, pi-ai, after years of frustration with existing tools. He emphasizes the importance of context management and offers technical details on API integration and model interoperability. The article also discusses challenges faced with self-hosting and API peculiarities.

Zhipu AI has released GLM-4.7, a new version of its General Language Model designed for advanced coding and multimodal tasks. It improves reasoning capabilities and supports both text and vision inputs, making it suitable for developers and enterprises. The model features enhanced APIs for real-time and batch processing, aligning with demands for more sophisticated AI applications.

The article details the author's frustrating experience trying to obtain a Google Gemini API key for a coding project. After navigating a confusing array of Google services and verification steps, the author ultimately gained access, but not without significant hassle and delays.

This repo lets you query multiple large language models (LLMs) and see their individual responses side by side. It then has them review and rank each other's outputs, with a designated Chairman LLM providing the final answer. The project is a simple, local web app meant for exploration and comparison of LLMs.

GitHub Chat integrates with various AI coding assistants like Cursor and Claude to facilitate instant understanding of codebases. It provides a straightforward API for indexing GitHub repositories and querying them for detailed information about their contents and technologies used. Unlike GitHub Copilot, GitHub Chat offers repository-wide analysis and a public API for developers.

The article discusses the implementation and refactoring of the ResizeObserver API, highlighting its advantages over older APIs and illustrating how to create a more user-friendly version. It provides step-by-step guidance on encapsulating the observer functionality, improving its usability through callbacks, and handling multiple elements efficiently. Additionally, it emphasizes the importance of refactoring for cleaner and more maintainable code.