AI coding agents

GitHub says it discovered 24 vulnerabilities in Android using its open-source AI security agent, describing it as automated vulnerability discovery at scale on real production software. The company published details in a blog post, and the report is drawing attention as a notable demonstration of AI agents doing practical security research on widely used code.

JetBrains has introduced Air, described by the company as a system of products built around agentic software development, where AI agents take on coding tasks alongside developers. The announcement is drawing attention from developers debating what it means for the future of IDEs and how JetBrains plans to compete in the fast-moving market for AI-assisted programming tools.

GitHub says its AI agent identified 24 vulnerabilities in Android applications, marking a notable demonstration of autonomous AI tools in security research. The findings highlight how AI agents are being put to work scanning for real flaws rather than just assisting developers with code. Security watchers are discussing what this means for the future of automated vulnerability discovery and app safety.

Engineering teams using AI coding agents are finding that continuous integration pipelines have become their biggest constraint, according to a report circulating among developers. As agents generate far more code and commits than human programmers, test suites and CI infrastructure struggle to keep up, forcing teams to rethink how they validate machine-written code at scale.

Developers working with AI agents are separating an agent's decision-making logic from the component that generates code or text, a pattern being discussed under the name Jev. The split lets a reasoning model plan while a writing model executes, and people in the field are debating whether this two-brain architecture improves reliability or just adds complexity to agent workflows.

The phrase 'Plan mode is dead' is spreading on Hacker News, attached to a blog post by Aymann Nadeem. Plan mode is a feature in AI coding tools, notably Claude Code, that lets the model sketch an approach before writing code. The post argues this way of working with AI assistants has run its course, apparently because newer agent capabilities make upfront planning less necessary. Commenters on the thread are debating the claim and what it means for developer workflows, though the full reasons are not clear from the snippet alone.