Tag
Anthropic is making Claude Code's auto mode the default for Pro, Max, and Team accounts starting August 14, reducing the need for manual approval prompts while adding safety features like prompt injection screening and hard deny rules.
Recommended to pay attention to Claude Code's capabilities, from which you can migrate harness-related features into your own product. Claude Code is a terminal agent programming tool introduced by Anthropic that supports natural language operations.
OpenAI launches an offline version of Codex as part of the ongoing AI competition.
A developer describes building a multi-engine agentic coding harness that routes sessions across Claude Code, Codex, and Ollama, selecting from twelve models per session based on task value.
Fius is a unified AI model aggregator tool that combines multiple AI providers like OpenAI, Google, Mistral, and DeepSeek into one code editor and API, with simple pricing plans.
Meta has launched Muse Code, a beta coding tool aimed at assisting developers.
Book-to-skill is an open-source tool that converts technical books into structured skills for AI coding agents, reducing token usage by 24x-51x by loading only the needed chapters on demand.
A practical tip on how to use coding AI more effectively. It lists 12 concrete prompt examples—such as having the AI read the code before modifying it, changing only the necessary parts, and writing rules into AGENTS.md—to reduce back-and-forth and make the rules stick long-term.
Cursor has released new plugins that give coding agents direct access to Google Workspace, enabling them to read, write, and act across Gmail, Drive, Calendar, Docs, and Sheets without leaving Cursor.
Ankur Sethi describes a personal workflow where he manually retypes LLM-generated code to maintain a deep understanding of his codebase and avoid cognitive debt, trading speed for comprehension.
Microsoft CEO Satya Nadella confirmed that the company is developing a 'super app' that integrates Copilot's chat, coding, and agentic capabilities, set to launch this year for both consumer and commercial use.
A developer shares their struggle with losing context when switching between Cursor, Claude Code, and Codex, and how they solved it using MEMMY, a tool that syncs chat histories into a shared memory hub for all agents.
Kat Coder 2.5 is a coding assistant model that delivers impressive performance even when run at Q4_K_M quantization.
Anthropic shares insights into the engineering challenges, architectural decisions, and agentic capabilities behind building Claude Code, their AI-powered coding assistant.
A developer questions whether a high-RAM MacBook Pro for local AI models could match cloud frontier models like Claude for coding, considering long-term costs.
AI coding startup Cognition has acquired Poke, an AI assistant known for its friendly personality, in a deal valuing Poke in the low nine figures. The acquisition aims to bring Poke's interaction model to Cognition's coding assistant Devin, highlighting the growing value of AI personality.
OpenCode Superapp combines the power of Codex with locally hosted AI models and voice capabilities for coding.
pigo is a command-line AI Agent rewritten in Go, supporting headless script mode and interactive REPL, capable of reading/writing files, executing commands, searching code, and compatible with multiple large model protocols, accompanied by an e-book.
An Ars Technica article comparing two approaches to AI coding harnesses: the lean harness of Claude Code and the context-rich semantic retrieval approach of Augment Code, featuring an interview with Augment Code's VP of Engineering Vinay Perneti.
A personal review of using the Qwen 3.8 model for agentic coding, praising its ability to handle complex tasks like integrating llama.cpp with Godot while noting issues with looping.