A developer explored loop engineering, a pattern where coding agents repeatedly execute tasks until a goal is met, and assessed its relevance for frontend and fullstack developers. The developer demon…
Anthropic released Claude Sonnet 5, its most agentic medium-sized AI model, replacing Sonnet 4.6 as the default for free and pro users. The model offers improved reasoning, tool use, and coding at low…
A developer accused Anthropic of embedding hidden detection logic in Claude Code version 2.1.91 that silently identifies users connecting through Chinese proxies using obfuscated Unicode tricks and da…
A developer built a free customer support AI agent for NextJS websites using Hexabot, OpenRouter, and Railway. The agent uses RAG to ingest website content and answer questions, deployed with a free P…
A developer accidentally built a closed-loop self-healing system for AI configuration after noticing repeated rule-writing without behavior change. The system uses three files—config-health.py, pendin…
A developer introduced a dual-layer monitoring system for AI agents that produces zero output on success, following Unix conventions of silence for normal operations. The system uses exit codes to com…
A developer created a self-verifying rule system for AI assistants after discovering that 15 rules for an AI assistant were followed zero times in 30 sessions. The system uses embedded markers like [✓…
Assembled open-sourced 143.dev, its internal infrastructure for running coding agents as a team, under an MIT license. The system runs multiple agent harnesses in sandboxes and integrates with tools l…
Loomcycle v1.5.0 enables co-authoring between agents and humans by introducing user-scoped MCP dispatch, config-declared static principals, and deep-merge configuration. The update allows agents and h…
A recent engineering graduate built a millimeter-wave radar prototype that uses FMCW technology and a neural network to classify building materials, specifically targeting asbestos detection. The proj…
Anthropic launched Claude Science, a workbench for scientific research, at its AI for Science event on Tuesday. The offering aims to expand revenue streams ahead of the company's planned IPO later thi…
Fenic, a new dataframe API that integrates large language models as first-class operators, was released on Hacker News. The tool allows users to query both structured and unstructured data using seman…
Anthropic's Claude Code v2.1.179 update defaults to leaking session URLs into Git history, exposing sensitive data. A fix is available via copy-paste command.…
Developer ArthurDEV44 released Paneflow, an open-source native GPUI workspace for running multiple coding agents in parallel terminal panes. Built in Rust on Zed's GPUI framework, the tool supports Cl…
Anthropic embedded hidden spyware-like code in Claude Code that covertly targets Chinese users, sending information such as timezone and proxy data by injecting it into prompt messages. The code route…
Anthropic released a beta version of its Claude Desktop app for Linux, expanding the AI assistant beyond Windows and macOS. The app includes Chat, Cowork, and Code interfaces, with official support fo…
A developer claims Anthropic's Claude Code CLI tool secretly encodes China-related proxy signals into system prompts sent to its AI model, potentially creating a covert classification channel. The all…
Anthropic released a beta version of the Claude Desktop app for Linux, supporting Ubuntu 22.04+ and Debian 12+ on x86_64 and arm64. The beta includes Chat, Cowork, and Code tabs but lacks Computer Use…
LiteLLM Agent Platform shipped the inline harness, a shared OpenCode harness that eliminates the need for per-agent pods, reducing infrastructure overhead for teams running 5–15 agents. This feature a…
Google announced the Gemini Enterprise Agent Platform's fully-managed, remote MCP server, enabling external AI agents to securely access Google Cloud resources like Model Garden models, prompt templat…