⚠️ Slack notification issue — Please reinstall if you were affected. Learn more →
로딩 중...
Starting April 24, GitHub changed its policy to use Copilot users' private repo interaction data for AI training by default. You need to know exactly where the opt-out link is and what data is actually in scope.
A detailed guide explaining the structure of the .claude/ folder—Claude Code's core configuration directory—and the role of each file within it, providing practical setup instructions for developers looking to effectively use Claude at the team level.
Introducing 'loop', a CLI tool that runs Claude and Codex side by side on tmux and lets them communicate with each other. The two AIs take on the roles of developer and reviewer, mimicking human pair programming.
A post introducing a prompting technique inspired by GAN (Generative Adversarial Network) principles to improve conversation quality with Claude — however, the original content is inaccessible due to network restrictions and cannot be verified.
A real-time incident response record in which an ML engineer, with the help of Claude Code, discovered and disclosed a supply chain attack hidden in litellm version 1.82.8 on PyPI within 72 minutes. It demonstrates that even non-security developers can detect and report malware using AI tools.
A post sharing how to run Claude Code fully offline on a MacBook by connecting it to a local LLM without an API key or cloud, useful for developers who want to use an AI coding assistant at no cost.
A developer shares how they built an AI agent for their portfolio site using IRC as the transport layer — enabling direct GitHub code analysis and visitor Q&A — running on a $7/month VPS. Going beyond the typical 'AI chatbot portfolio' that simply feeds a resume into an LLM, this system provides concrete answers grounded in the actual codebase, making it a noteworthy practical example of AI agent architecture design.
Chroma's newly released 20B parameter agentic search model claims frontier-LLM-level retrieval performance at 1/10 the cost and 10x the speed — though a significant controversy over failure to cite prior work has emerged in the community.
A framework that writes and shares agent control logic (harness) in natural language instead of code, executed by a shared runtime, enabling comparison, reuse, and analysis of design patterns.
An autonomous software evolution framework where LLM agents directly exercise product specs at 1000x speed to find bugs and auto-merge PRs
A TypeScript library that combines Playwright browser automation with LLMs to reliably extract structured data from web pages, with a focus on token efficiency and JSON parsing stability.
An open-source project that achieves 74.6% on LiveCodeBench by wrapping a frozen 14B model with a structured generation-validation-iterative-repair pipeline at inference time. It draws attention for approaching frontier-level coding performance on a single consumer GPU—without any fine-tuning, API, or cloud.
A post about giving Claude AI access to a macOS environment, sharing real-world use cases for integrating a local computer with AI.
An analysis post arguing that the perceived sudden reduction in Claude Code limits is not an actual limit decrease, but rather a spike in token consumption driven by the 1M context window.
A project that designs a hierarchical memory structure (Cognitive Architecture) based on plain-text files to address Claude Code's inability to retain memory across sessions. A practical reference for developers who want to use AI coding assistants consistently over the long term.
A Kubernetes-based workflow automation tool where an AI agent writes code from GitHub Issues or Linear tickets, automatically fixes CI failures, incorporates review comments, and merges PRs — all without human intervention. It stands out for fully automating the entire ticket-to-PR cycle.
The Claude Code agent autonomously combined and improved existing jailbreak attack algorithms, achieving 40% ASR against GPT-OSS-Safeguard-20B and 100% ASR against Meta-SecAlign-70B.
A triple-layer security framework where an independent Watcher agent intercepts threats in real time before AI agents executing shell commands get compromised
A learning project that reimplements the core architecture of Claude Code in Swift across 9 stages to understand why it works so well, directly validating the design philosophy of 'fewer tools, trust the model more.'
A post sharing the experience that sending a short greeting like 'hey' to Claude first can consume a significant portion of your total usage limit, raising awareness about prompt-writing habits for token conservation.
