Full-text search across 66124 articles. Combine with topic and date filters; results sorted by relevance.
Anthropic announced a team of agents that formalized Fermat's Last Theorem, producing over ten million lines of Lean code, but the author argues that such artifacts are of limited utility because humans must still verify…
1Password has become embroiled in a right-wing controversy after funding a Linux project, according to a report. The article notes that DHH, creator of Omarchy 4, claimed most of its code was written by GPT-5.5, but he a…
Anthropic's public 'skills' repository, which packages reusable agent workflows into portable SKILL.md files, gained 277 stars in a day. The collection helps coding agents handle repeatable tasks like document and spread…
GitHub Copilot Workspace, an AI-powered development environment, is being evaluated as a potential replacement for traditional IDEs, with proponents citing its ability to streamline coding tasks through natural language …
A developer has released btp-guard, an open-source Python package that performs in-memory AST-based safety checks on code blocks generated by local LLM agents before execution. The tool parses Python, SQL, and Bash code …
IBM Distinguished Engineer Grant Miller has introduced a code review framework called Outcome Reviews, which shifts human reviewers' focus from syntax and implementation details to business intent, acceptance criteria, a…
A developer criticized an AI-generated code comment from Anthropic's Claude for asserting that skipping a full collection walk is 'the usual case,' a claim the model cannot verify and that misleads future readers about s…
The Register reports that Debian has voted to allow contributors to use AI in coding, with disclosure optional but quality mandatory. The decision marks a significant policy shift for the open-source project, potentially…
Antigravity 2.0, an AI coding assistant, has introduced Git Version Control System (VCS) Controls directly in its right-side panel, along with an embedded terminal tab, to provide developers with a unified view of all ch…
A developer highlights the use of 'Skills' as a solution to repetitive prompting in AI coding agents, describing a folder-based standard that works across tools like Claude Code, Cursor, and Copilot. The post explains ho…
A developer released a weekly digest of seven rules for senior C#/.NET engineers using Cursor, covering topics such as enforcing strict boundaries for database logic, using Result objects instead of nulls, adding OpenTel…
The open-source Continue IDE for VSCode, which offered offline AI-assisted coding via Ollama, has been formally archived and marked read-only after being acquired by Cursor, according to a Hacker News thread. The consoli…
A developer who cannot write code in any programming language used agentic coding tools to create Hackerznews, a personal Hacker News client, and shared it on Hacker News. The app features an updated UI, dark mode, respo…
Splunk released security updates for 17 vulnerabilities, including a critical remote code execution flaw (CVE-2026-76404) in Splunk MCP Server with a CVSS score of 9.1, affecting Splunk AI Toolkit and Splunk Connect for …
Passproof, a new open-source tool released under the MIT license, blocks AI coding agents from claiming tests passed unless the test runner's output appears in the same chat turn. The tool, installable via `npx passproof…
SpaceX has acquired Cursor, an AI coding tool founded by MIT graduates, integrating its advanced AI coding capabilities with Grok and massive GPU infrastructure. The acquisition connects MIT founders with SpaceX's resour…
VectorNode has published a quickstart guide demonstrating how to make OpenAI-compatible API requests using Python, JavaScript, and PowerShell, with example code available in its repository. The guide instructs users to r…
Anthropic began invisibly watermarking text generated by its newest Claude models on August 2, 2026, with older models migrating over subsequent months, prompting a wave of subscription cancellations. The statistical wat…
A blog post by lr0.org argues that Lisp is a superior target language for AI code generation because it emphasizes high-level abstractions over mechanical state management, citing a quote from Abstract Heresies and contr…
Developer Matt Pocock shares five agent skills he uses daily to enhance AI coding assistants like Codex, covering research, design review, React best practices, code simplification, and end-to-end testing of desktop apps…