Full-text search across 32020 articles. Combine with topic and date filters; results sorted by relevance.
Anthropic's Claude Code team member Thariq Shihipar discussed the development of the AI coding tool in a podcast with South Park Commons Partner Evan Tana, revealing that the team removed Plan Mode and that RAG is becomi…
Agentty, a drop-in alternative to claude-code written in C++26, is now available as an 11.0 MB static binary with sub-millisecond startup. The tool supports multiple AI models including Claude, GPT, Groq, OpenRouter, and…
A developer found that Cursor, an AI code editor, generated a login endpoint with a SQL injection vulnerability (CWE-89) by interpolating user input directly into a query string. The developer warns that AI models traine…
A developer explains that a public security scanner for vibe-coded applications can check deployed surfaces for misconfigurations, exposed secrets, and missing headers, but cannot assess authenticated logic, source code,…
A developer shipped v0.4.0 of cursor-plugin-cc, a Claude Code plugin that keeps one loop running Claude plans, Cursor's Composer writes the code, and Claude reviews the diff. The new `/cursor:adversarial-review` command …
The Ornith-1.0 family of open-source coding models was released under the MIT license, achieving state-of-the-art scores on agentic coding benchmarks including 82.4 on SWE-Bench Verified and 77.5 on Terminal-Bench 2.1. T…
A developer built the Adversarial Resilience Score (ARS), a new metric for AI-generated code that measures how resilient code is against adversarial attacks. ARS is computed as the mean of per-attack scores (mitigated, p…
Simon Willison shared a GitHub code-frequency chart for his open-source project Datasette, showing a spike in activity that he attributes to coding agents and models including Opus 4.8, GPT-5.5, Fable 5, and GPT-5.6 Sol.
A developer in Port Harcourt, Nigeria, reports that a single heavy coding session with Claude Code consumed 1–1.5 kWh—more than the average Nigerian's daily electricity ration of 0.45 kWh. Citing measurements by Simon P.…
A developer study found that Claude Code sends 33,000 tokens before reading a prompt, while OpenCode sends only 7,000, making Claude Code significantly more inefficient in cache strategy and token usage. The findings wer…
Meta's Muse Spark 1.1 model outperforms GLM-5.2 in coding benchmarks and costs less per task, according to Artificial Analysis. The model scores 71.3 on the Coding Index versus GLM-5.2's 68.8, with a price of $0.26 per t…
A developer warns that 'vibe-coded' products—built rapidly with AI agents—often fail in production due to unmaintainable code, lack of domain modeling, and accumulating technical debt. Studio Labs, the developer's compan…
A new tool called Mosh Coding allows users to generate branded landing pages with customizable social links, affiliate links, hashtags, and AI-generated hero images based on music genres. The platform supports per-platfo…
R3, a local code review tool for AI agents, launched on Hacker News. It enables developers to leave line-specific feedback on agent-generated diffs and documents, tracking comments to resolution outside of chat interface…
ReviewCerberus, a free open source AI-powered code review tool for GitHub Actions, has been released. It analyzes git branch differences and generates comprehensive review reports covering logic, security, performance, a…
Kastra, a runtime authorization tool for AI coding agents like Claude Code, Cursor, and Codex, intercepts agent tool calls and evaluates them against deterministic policies before execution. The tool was created after a …
Databricks tested Zhipu AI's open-weight model GLM-5.2 in July 2026 and found it matches Claude Opus 4.8 on enterprise coding quality while costing 34% less per task. The model scored 62.1% on SWE-bench Pro and 81.0% on …
Arbor v2.4.0, a code graph MCP server, was released in July 2026 with support for the MCP 2026-07-28 protocol, Tasks extension, MCP Apps for interactive UI, and Streamable HTTP transport. The update enables AI agents to …
Bastion, an open-source orchestrator for running background coding agents on self-hosted Linux infrastructure, was released. Each agent runs in a separate Cloud Hypervisor VM with a reproducible dev environment, supporti…
Sonn, a reasoning layer for coding agents, uses persistent memory to anticipate and prevent mistakes before they occur. Built for Claude Code, it runs locally and steers agent behavior by reasoning over past decisions, r…