Full-text search across 60723 articles. Combine with topic and date filters; results sorted by relevance.
Session Porter, an independent tool not affiliated with Anthropic, lets users move Claude Code conversations between Mac and Windows computers in any direction by packing sessions into a single zip bundle and unpacking t…
Anthropic will make auto mode in Claude Code the default for new sessions on Pro, Max, and Team plans starting August 14, putting AI in charge of reviewing actions. In a controlled experiment with 1,053 paid professional…
AI coding tools have reached $60 billion valuations while hiring for junior developers continues to decline, according to a Forbes report by Josipa Majic Predin. The shift is splitting software careers into two distinct …
Jovian's founder used Anthropic's Claude Opus 5 to refactor the Jovian codebase from a Next.js 11 frontend and Flask backend to a full-stack TanStack Start app, moving over 5,700 lines of code and updating hundreds of im…
A developer has created an output style for Claude Code that enforces ASD-STE100 Simplified Technical English, a controlled language originally developed for the aerospace industry. The style rules limit sentence length,…
Anthropic will make auto mode the default permission model in Claude Code starting August 14, shifting from opt-in to opt-out autonomous execution. In auto mode, a second Claude Sonnet 5 model grades consequential action…
Anthropic's Claude Code sessions on macOS and Linux can now send messages to each other, enabling cross-terminal context sharing. The feature allows users to ask questions and receive answers between sessions, and Claude…
Fractal Manifold launched a crowdfunding campaign for the Token Monitor, a 4-inch ESP32-S3 desktop display that tracks AI coding assistant usage in real time. The device shows quota consumption, session limits, token cou…
Microsoft has open sourced code-testing-generator, a polyglot unit-test agent in the MIT-licensed dotnet/skills repository that reads a repository to detect language, test framework, conventions, and build/test commands …
A developer known as CraniusMaximus has released session-tax, an open-source tool that analyzes Claude Code session transcripts to identify idle skills and estimate their token overhead. The tool reads local transcript f…
A hidden bug in Anthropic's Claude Code scheduling layer can re-fire single-run commands when background tasks wake up, potentially doubling API costs by duplicating database writes, pull requests, or agentic searches. T…
QAInsights published a blog post introducing Pleasantries, a small Python script that prevents AI coding command-line interfaces from wasting tokens on casual greetings like 'hi', 'ok', or 'thank you' by intercepting and…
Chipmates released cctap, an open-source tool that adds a status line to Claude Code sessions, turning red when a session waits for user input and enabling a system key to jump to the waiting session. The tool installs w…
A developer released 'write-normal', a Claude Code skill that strips recognizable signs of AI writing from prose, such as fake wisdom, rhetorical devices, inflated vocabulary, filler, sycophancy, and over-formatting. The…
A developer built a two-agent code review loop for local Ollama workflows, splitting the job into Reviewer and Verifier roles to reduce hallucinations and generic advice. The workflow is packaged into HAICHI, a desktop w…
OpenClaw and Ollama released a full-stack agent architecture with open code and datasets, demonstrating 30% better task completion rates through persistent memory, tool use, and adaptive decision-making. The integration …
Agent-Up now treats the browser as part of the workspace runtime, giving each AI coding agent its own isolated browser session, application tabs, and runtime state. This allows agents to interact with the web app through…
A developer is preselling an Obsidian AI plugin for $19 before writing any code, citing research that shows licensing and maintenance are major pain points for paid plugins. The plugin, which provides weekly 'checkups' f…
Angela (Lo An), a practitioner in CI and testing, argues that coding agents' ability to quickly fix failing CI logs and open pull requests can be dangerous if teams treat a green pipeline as proof of safety. She emphasiz…
On July 16, Beijing-based Moonshot AI released Kimi K3, a 2.8-trillion-parameter open-weight AI model, which independent accounts call the largest ever built. Three days later, Moonshot paused new signups due to demand n…