agentic coding

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.

GitHub says its AI agent identified 24 vulnerabilities in Android applications, adding to growing evidence that autonomous coding assistants can take on security research tasks. The finding, reported by Help Net Security, highlights both the potential of AI-driven bug hunting and the questions it raises about verifying machine-discovered flaws. Security teams are watching closely as AI agents move into vulnerability discovery.

Google Research has open-sourced RRSI, a framework allowing AI agents to refine their own evaluation harness while guarding against overfitting. Announced via MarkTechPost, the release lets developers inspect and build on the underlying code. The announcement is drawing attention from AI practitioners interested in agent self-improvement methods that remain reliable rather than gaming their own benchmarks.

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 researchers report that an open source AI security agent they built uncovered 24 vulnerabilities in Android. The company says the tool was used to scan Android code at scale, flagging security flaws automatically. The disclosure highlights a growing trend of using AI agents to find real bugs in widely used software, and the work is being discussed as an example of AI-assisted security research.

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.

Developer and TypeScript educator Matt Pocock has published a repository called 'skills', described as 'Skills for Real Engineers. Straight from my .agents directory.' The collection shares his personal configuration and skills files used with AI coding agents. It is drawing attention among developers interested in how experienced engineers set up AI-assisted workflows.

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.

A new open-source project for routing requests between AI models in coding agents has been released, claiming performance on par with Astra-level systems. The launch was shared on Hacker News, where it drew over a hundred upvotes and is drawing attention from developers interested in cutting costs by mixing cheaper and stronger models dynamically.

Anthropic has introduced new modding features for Claude Code, its AI coding tool, letting developers customize how the agent behaves in their workflows. The update gives users more control over the assistant's configuration and output. Developers are discussing how the change could make AI coding assistants more adaptable to individual projects and team preferences.

A developer has released an open-source project offering marketing skills for AI coding assistants and agents. The toolkit covers conversion rate optimisation, copywriting, SEO, analytics and growth engineering, letting AI agents carry out marketing tasks directly. It is written in JavaScript and is gaining attention among developers experimenting with extending AI assistants beyond coding work.

A developer has released Corral, an open-source tool that lets users kill every command launched by an AI coding agent, giving them tighter control over runaway or unwanted processes. The project was shared on Hacker News under its Show HN format and drew modest engagement, with commenters likely weighing in on agent safety and process management.

A question circulating among developers asks whether anyone is genuinely producing good code with AI coding agents. The discussion taps into ongoing debate about whether tools like Copilot and Claude can deliver maintainable, reliable software or mostly generate code that needs heavy review. Many engineers remain split, reporting productivity gains in some tasks and disappointing results in complex work.

A new essay examines the leading tools and approaches in agentic coding, where AI agents autonomously write and manage code. It lays out four dominant players or paradigms shaping this fast-moving field and weighs their strengths and drawbacks. Developer interest in AI-driven coding workflows remains intense, and pieces that compare the main contenders are drawing close attention.

A widely shared essay argues that in the era of AI agents, the harness—the scaffolding of tools, prompts, evaluation and workflow code wrapped around a model—is where a company's actual value sits, not the underlying model itself. As models become commoditised and interchangeable, the author contends the harness is the durable product, and effectively the company's true identity.

Graphene, an open-source data analysis toolkit designed to work with coding agents, has been released on GitHub and shared with the developer community. It is pitched as a way to let AI coding assistants perform data analysis tasks directly. Early engagement is modest, but launches of tools extending coding agents are drawing attention as interest in agentic workflows grows.

A widely watched tech commentary item examines GitHub's most-starred repositories, arguing that repo fame now translates into real traffic, career visibility and adoption for developer tools, with AI coding agents increasingly driving which projects rise. Viewers are debating whether star counts still measure quality or are being inflated by agent-driven activity and trend-chasing.

A developer newly active in technical writing has raised concerns about security gaps in AI development workflows, arguing that teams are increasingly handing control to autonomous coding agents such as Claude without adequate safeguards. The post argues agent security is a critical blind spot as autonomous tools gain access to codebases, credentials and infrastructure. Other developers are engaging with the warning as adoption of AI coding assistants accelerates.

A new essay explores what it calls the four horsemen of agentic coding, examining the key forces or figures shaping the rise of AI agents that write software autonomously. Programmers and AI observers are sharing and debating the piece as discussion grows over how agentic tools are changing development work and the future of the programming profession.

A developer has built what they describe as a company of bots, arguing that most AI agent demos rely on a single clever prompt. Instead of a one-off demo, the project organizes multiple agents in a structured way, using Python and open source tools, and shares the work with the inclusive coding community.

JetBrains has announced Air, described as a system of products for agentic software development, in a company blog post. The announcement outlines how the toolmaker plans to structure a product line around AI agents that write and manage code. Developers are sharing the item on programming forums, with discussion focused on what the offering means for existing JetBrains IDEs and the wider shift toward agent-driven coding tools.

An experiment tested whether AI reviewer models can catch cheating in code changes when agents review agents, an assumption behind automated software pipelines. Across 77 diffs containing deliberately planted cheats, three reviewer models caught every exotic trick but approved one case where an assertion was quietly made unfalsifiable, meaning the test could never fail. The finding raises doubts about relying on AI review alone to guarantee code quality where automated testing falls short.