Full-text search across 58571 articles. Combine with topic and date filters; results sorted by relevance.
Cline can run as a fully autonomous coding agent on local hardware by connecting to Ollama instead of cloud providers like Claude or GPT-4, keeping all inference on the user's own machine. The setup requires raising Olla…
A developer argues that AI coding agents fail in production because large language models assume smooth, continuous state transitions while software is governed by discrete, cliff-like failure modes, a phenomenon they ca…
DoozieSoftware has released DoozCTL, an open-source repository standards engine designed to persist project knowledge as deterministic artifacts in the repository, rather than relying on AI coding assistants to rediscove…
Anthropic's Claude Code 2.1.257 stores OAuth tokens for remote MCP servers in plaintext JSON on Linux, protected only by file permissions, contradicting its documentation that claims tokens are 'stored securely'. The fil…
A developer reports cutting 80%+ of context overhead in AI coding agents by consolidating tools and dynamically activating them, benchmarking that OpenAI's Codex loads 79 tools and consumes 14,534 tokens on a fresh sessi…
Since June 2025, frontier AI labs have withdrawn or restricted model access affecting named coding tools or peer labs four times, according to a ledger compiled by an unnamed source. The instances include Anthropic limit…
Nick Basile has published version 2.2.0 of his personal coding rules, a set of guidelines for architecture, Laravel, testing, databases, APIs, Inertia.js, React, Tailwind, HTML/JSX, and accessibility. The rules emphasize…
AI coding has erased the supposed advantage of statically typed languages, according to an analysis arguing that AI models do not benefit from type systems the way humans do. The article claims that AI's expensive mistak…
Anthropic's Boris Cherny, a creator of Claude Code, said in a Y Combinator interview that the team removes over 80% of the system prompt with each new model release, and advised users to periodically delete their CLAUDE.…
A developer from INFORMAT discusses the design of data models in low-code platforms, emphasizing the importance of metadata and treating business entities as objects rather than pages. The post argues that field semantic…
Apple's Swift 6.2 introduces Default Actor Isolation in new Xcode 26 projects, automatically isolating app target code to the main actor, reducing the need for explicit @MainActor annotations. The @MainActor attribute, a…
Cursor, launched by Anysphere in 2022, offers more accurate inline autocomplete with a 28–35% acceptance rate and a familiar VS Code experience, while Windsurf, formerly Codeium and rebranded in 2024, excels in autonomou…
JetBrains released ReSharper 2026.2, introducing ACP-based AI agent support in Visual Studio with Junie in Preview, enabling developers to choose their own agents and models without vendor lock-in. The release also exten…
X-cmd v0.9.14 adds two command-line modules, `x cve` and `x cwe`, for querying CVE vulnerability IDs and CWE weakness categories, respectively. Founder and CEO Edwin Lee argues that as AI agents mass-produce code, they s…
NEAT Technologies released NEAT, an open-source tool that fuses static code analysis and OpenTelemetry runtime telemetry into a single live graph to reduce AI agent hallucinations and improve debugging accuracy. The tool…
AI coding tools are flooding open-source projects with low-quality pull requests, overwhelming volunteer maintainers and driving some to quit. GitHub is exploring AI-based filtering to help maintainers cope with the surg…
Raycast launched Glaze, an all-in-one vibe-coding app for Mac that lets users build and share desktop apps without traditional programming. The author built three apps in the first month, finding the process delightful d…
Claire tests GLM-5.2, an open-weight model from Z.ai, in her ChatPRD codebase, finding it production-grade and capable of replacing Opus for some coding workflows. The model benchmarks near Claude Opus 4.8 and above GPT-…
A developer found that coding agents' success reports are unreliable, catching three false positives in a single session: a stale-cache build pass, a mislabeled test result, and a half-applied rename. The developer argue…
A $120 million exploit of Nexus Protocol, which had passed three AI-powered code audits, reveals a new cybersecurity battleground where AI tools accelerate both defense and attack. Attackers are using the same AI models …