Developer Nathan Langley released Orb, a self-hosted AI assistant backend that proactively messages users via an iOS companion app. The open-source server runs on Windows (macOS planned), uses Claude …
A developer with limited coding experience built a WebGPU multiplayer game using Claude Code, an AI coding tool from Anthropic. The game, which matches players on mouse and keyboard, is ready to deplo…
A growing number of engineers are experiencing tech burnout in the AI era, driven by a loss of the 'maker' feeling when AI generates code, according to an analysis of developer sentiment. The shift fr…
Anthropic deleted over 80% of Claude Code's system prompt for Opus 5, and the model became more intelligent, according to Claude Code creator Boris Cherny at YC Startup School 2026. Cherny shared a pl…
A new field report from OpenAI reveals that coding agents, primarily Codex and Claude Code, enabled small teams to modernize critical scientific software in genomics and other fields across eight proj…
FedTerm, a Claude-native terminal for macOS that opens with a global shortcut like Spotlight, has been released on Show HN. The app floats above other apps, records command history, and integrates wit…
A staff letter from AI labs including OpenAI and Anthropic calls for government-backed safety standards to prevent a 'race to the bottom' in risk management, arguing that shipping fast often takes pre…
Anthropic's Claude Code has emerged as the preferred AI coding agent among enterprise engineers, accounting for roughly 4% of all public GitHub commits by February 2026 with a daily peak of 326,000 co…
Claude Code demonstrates that large language models can now audit encryption algorithms by analyzing state transitions and mathematical properties to spot flaws, moving beyond simple bug detection to …
AI chip stocks are experiencing a market correction driven by capex fatigue, concentration risk among cloud service providers, and expectation inflation, according to an analysis of the current cycle.…
Claude Code, an AI coding agent from Anthropic, uses a system prompt that instructs it to assume the user is absent and to execute tasks without asking permission, eliminating the confirmation loop th…
Snowflake Inc. on Tuesday launched the Cortex AI Gateway, a centralized control plane to govern, secure, and track autonomous AI agents across internal and third-party systems, addressing security and…
A developer distinguishes between silent hooks that fix mechanical issues and loud hooks that teach agents by rejecting incorrect actions. The loud reject pattern is demonstrated with a Flyway migrati…
Developers using AI coding tools like Cursor and Claude Code face budget shocks from agentic spend loops, as vendor dashboards provide only post-hoc accounting rather than real-time cost controls. Loo…
Cursor (v0.4x) outperforms Windsurf and Claude Code in real-world coding tasks, according to a developer's hands-on test of refactoring a legacy React codebase to Next.js 14. The test measured pricing…
Developer Thiago Perrotta used the drskill linter to scan Claude Code skills bundled in a plugin, working around a known limitation by symlinking the plugin's skill directory into a temporary .claude/…
Developer Yuji Suzuki split his AI Sandbox Environment + DockMCP repository into three independent repos after using the setup to build and ship a real iOS app, とけるよ. The split separates the devcontai…
A new platform called NoClick enables users to build always-on background AI agents using existing subscriptions to tools like Claude Code, Codex, OpenCode, Hermes, and OpenClaw. The platform automate…
An unnamed developer reports that Claude Code, an LLM agent, can hallucinate by describing a cat photo as a bridge when the file is renamed to 'golden_gate_bridge.jpg', revealing a tendency to priorit…
Unverified AI summarization poses a due-diligence failure in legal workflows, according to a technical analysis of Claude Code and LLM agent deployment. The article recommends citation enforcement, cr…