AI Briefing#coding-assistant
The latest AI and developer news about #coding-assistant, with the original source and a short summary.
The latest AI and developer news about #coding-assistant, with the original source and a short summary.
Built a chat UI for Gemma-4-E4B using a Qwen-series model in about 8 minutes.
OpenAI has unveiled a major update to the Codex app that automates developer workflows by integrating computer control and image generation capabilities.
Anthropic has launched Claude Opus 4.7, a flagship model with self-verification capabilities and high-resolution vision.
Claude Code has been redesigned to run parallel coding agents within a single desktop workspace.
OpenHarness, a lightweight open-source Python infrastructure that turns LLMs into real agents, has been released.
Claude Code has introduced a Monitor Tool feature that uses background processes to operate only in specific situations.
Orca, an open-source development tool that lets you run and manage AI agents in parallel within isolated environments, has been released.
It is an open-source extension tool that introduces an engineering lifecycle and multi-agent verification structure to improve the reliability of AI coding agents.
An open-source system that centrally manages and visualizes work context across AI coding agents.
OpenAI has released GPT-5.4 mini and nano, high-performance small models optimized for coding and subagent tasks.
The **Slack Agent Skill** has been released, using coding assistants to handle everything from building to deploying Slack agents in one go.
OpenAI has built the Codex App Server, which unifies management of Codex agent logic across various environments.
Moonshot AI's latest model **Kimi K2.5** is now available through **AI Gateway** without a separate account.
OpenAI has released GPT-5.1 on its API platform, which optimizes reasoning time according to task complexity.
In a Kakao survey, 98.9% reported improved productivity, while Stack Overflow traffic has decreased by nearly 50% from its peak.
Replit Agent has significantly expanded its app-building capabilities, now supporting any development framework and language beyond specific app types.
xAI has released Grok Code Fast 1, a fast and low-cost reasoning model optimized for agentic coding workflows.
Continue CLI enables developers to build asynchronous cloud agents that perform complex coding tasks without disrupting their workflow.
OpenAI has released GPT-5, its next-generation model optimized for coding and agentic tasks, via the API.
Replit launched a new AI Assistant and announced enhanced visual capabilities for Agent along with a new checkpoint-based pricing model.
Mistral AI unveiled Codestral Mamba, based on the Mamba architecture capable of linear inference and unlimited sequence handling.
Qwen has released CodeQwen1.5-7B, an open-source code-specialized LLM trained on 3 trillion code tokens.
Introduces how to build a personal coding assistant optimized for a specific codebase using Hugging Face's public repositories, along with HugCoder.
Introduces how to fine-tune StarCoder with ChatML and DeepSpeed to build the conversational coding assistant StarChat.