AI code generation

Kernel developer Greg Kroah-Hartman, maintainer of the Linux kernel's stable branch and a central figure in open-source security, has a talk examining software security in the age of large language models. The discussion covers how LLM-generated code and LLM-assisted workflows affect vulnerability handling, code review and trust in the open-source supply chain. It is drawing attention from developers weighing AI's risks and benefits for core infrastructure.

System76 has announced that its COSMIC desktop projects will no longer accept code submissions containing LLM-generated content. The company behind Pop!_OS says pull requests relying on AI-generated code will be rejected, citing the problems such content has caused for developers. The move adds System76 to the growing list of open source projects drawing lines around AI use in contributions.

A question on Hacker News asks whether developers are genuinely producing good code with AI coding agents. The discussion invites practitioners to share whether these tools, increasingly embedded in everyday software work, deliver code that is reliable and maintainable rather than just fast to generate. It reflects growing scepticism amid heavy industry promotion of AI-assisted programming, with developers weighing real-world results against the hype.

A developer used the AI assistant Claude to build an interactive simulation of an O'Neill cylinder, a proposed rotating space habitat whose spin generates artificial gravity through centrifugal force. The result is a walkable 3D environment the creator says is physically accurate, letting users explore the inside of the station and see how the habitat's dimensions, rotation and lighting would actually behave.

Akka is running an experiment applying spec-driven development to AI-assisted delivery across 65 of its open source repositories. The approach centres on defining clear specifications first, letting AI tools generate and validate implementation against them. The initiative is drawing attention from developers weighing how specification-first workflows could make AI coding agents more reliable at scale.

JetBrains has published a developer diary explaining how it built a retrieval-augmented generation pipeline for semantic code search, walking through field notes and practical lessons from the process. Developers are discussing the technical approach, trade-offs, and what it means for AI-assisted coding tools and code navigation in IDEs.

The MLC community has published TIRx Harness, an open-source compiler harness designed for agentic GPU programming. The tool lets AI agents write, compile and test GPU kernels through a structured compiler interface, aiming to make automated low-level code generation more reliable. Discussion is focused on how compiler tooling like this could accelerate machine learning systems development.

OpenAI's Codex, the company's AI coding agent built on its GPT models, is generating renewed discussion as developers and tech commentators weigh it against ChatGPT. The conversation centres on how the two tools fit together: ChatGPT as the general assistant and Codex as a specialised tool for writing and reviewing code inside developers' workflows.

OpenAI has begun embedding invisible watermarks into text generated by ChatGPT and its Codex coding tool for users in the European Union. The move, reported by BleepingComputer, is being read as a step toward compliance with EU transparency rules around AI-generated content, allowing machine-generated text to be identified. The news is drawing attention to how AI firms verify and label output, and to questions about privacy and how such detection will work in practice.

Amazon Web Services announced a new agent skill that lets coding agents use Amazon SageMaker's optimized generative AI inference capabilities. The integration is aimed at developers building AI-powered coding assistants who want managed, low-latency model serving through SageMaker, extending AWS's push to position SageMaker as infrastructure for the fast-growing agentic AI developer ecosystem.