Full-text search across 61845 articles. Combine with topic and date filters; results sorted by relevance.
JetBrains Research has developed the AIDEs Framework, a model for understanding AI development tools, after almost two years of AI product and market research. JetBrains estimates Anthropic's Claude Code is used by aroun…
Alibaba Group has open-sourced its internal AI code review tool, Open Code Review, which has served tens of thousands of developers and identified millions of code defects over the past two years. The CLI tool reads Git …
Cursor's "Import VS Code Configuration" feature copies only extension names, not versions, from Visual Studio Code, so the agentic IDE installs whatever version Open VSX labels newest, according to a report on the extens…
AI coding assistants can generate code faster, but without coordinated downstream improvements, teams face review, testing, and deployment bottlenecks, according to a new analysis of the 'agentic software factory' concep…
A developer warns that AI coding tools like Claude Code produce 'almost right' code that passes a glance but fails in production, creating a circular trust problem when the same AI writes and verifies code. To solve this…
Docker's sbx sandboxes can now be connected to VS Code over SSH, letting developers compile and run code inside an isolated microVM with secrets protection and network policies instead of on the host machine, according t…
Per-diff code review cannot detect regressions in AI coding agents, because the changes that break them most — vendor model-alias updates and server-side changes — produce no diff to review, according to an evals-and-ver…
A working AI agent kill switch must cut the agent's credentials or network path rather than rely on a dashboard button, because a UI stop flag only takes effect on the process's next loop iteration and cannot halt an age…
An engineer running an AI-native delivery operation argues that as AI agents generate most code, the artifact of record should shift from source code to human intent, with code treated as governed output. The author prop…
Data scientists are shifting from writing code to constructing feedback systems that guide AI agents, according to Robin Linacre, creator of the Splink Python library. In a real-world test, an AI agent profiled Splink's …
Pixel Agents, an open-source tool by developer pablodelucca, turns AI coding agents running in terminals into animated pixel-art characters in a virtual office, with a VS Code extension and standalone CLI available via V…
A cluster of papers released today finds that passing tests and other common signals for judging AI-written code are unreliable, with repair agents' tests failing to distinguish correct fixes from no-ops nearly half the …
Evan Marshall, co-founder and CTO of Ito.ai, said in the Root Cause podcast that AI code generation can at most double a developer's speed if coding was half their job, and that once generation is free, the bottleneck sh…
Anthropic built an in-house version control system called Scion and fully migrated its monorepo off git in five months, after the company's average merged code changes rose from roughly 2,500 per day in May 2026 to over …
Anthropic built an in-house version-control system called Scion, developed by a team of seven, after its daily code merges grew from 2,500 in May to over 30,000 by September, the company said. Anthropic reported the new …
Anthropic built an in-house version control system called Scion and fully migrated its monorepo off git in five months, after its average merged code changes grew from about 2,500 per day in May 2026 to over 30,000 per d…
A veteran developer with 25 years of test-driven development experience describes abandoning TDD after transitioning to agentic coding, arguing that forcing AI agents through increments optimized for human cognition nega…
Tessl researcher and engineer Amy Heineike argues that as coding agents author the vast majority of code, a new role she calls the "harness engineer" is emerging to manage AI-authored code and maintain software quality. …
CodeRabbit has launched CodeRabbit Security, a tool that hunts application-specific vulnerabilities across the entire codebase, showing evidence and moving supported findings into remediation within the development workf…
Hannes M. (hmans) open-sourced Chatto, a self-hostable team and group chat app, and revealed that he has not written a single line of code since February 2026, relying instead on AI coding agents. He uses a €200/month Op…