AI code generation

A developer has built AI-assisted clones of every single Adobe application, from Photoshop to After Effects, using the 'vibe coding' technique of prompting large language models to write the code. The project is drawing wide attention online, with hundreds of thousands engaging with it, as viewers debate how far AI-generated software can go in replicating professional creative tools that normally cost substantial subscriptions.

A Tedium essay examines ArtCraft, a startup building creative applications largely through AI-assisted 'vibe coding', and asks what that approach says about Adobe's dominance in creative software. The piece argues that rapidly generated, AI-built tools challenge the long development cycles behind Creative Cloud, raising questions about whether Adobe's incumbency is vulnerable to cheaper, faster rivals.

Microsoft has published MXC, an open-source sandboxed code execution system, on GitHub. The tool is designed to run untrusted code in isolated environments, a common need for AI agents, automated coding assistants and secure server-side execution. Developers are discussing the release and what it offers compared with existing sandboxing options.

An artificial intelligence company has announced an initiative to protect critical infrastructure and open-source software projects from threats posed by AI. The move reportedly targets risks such as automated attacks, malicious code generation, and supply-chain manipulation affecting essential services and community-maintained software. Details of the program's methods and partners remain limited in early reporting.

A developer has released a small language model, built by finetuning Alibaba's 1.5-billion-parameter Qwen, that they say performs close to GPT-4o at generating bash commands despite being far smaller. The project, published as a Show HN submission, is drawing attention among developers interested in whether compact open models can match much larger proprietary systems on narrow coding tasks.

Greg Kroah-Hartman, the longtime maintainer of the Linux kernel's stable branch, is featured discussing what large language models mean for software and kernel security. The talk examines how AI-generated code affects maintenance, review practices, and vulnerability risks in widely used open-source infrastructure, and it is drawing attention among developers weighing the benefits and dangers of AI-assisted programming.

Insignary has launched Clarity AIR, a tool designed to identify hidden open-source components and AI-generated code in software. The product aims to give organisations visibility into code provenance amid growing concerns about untracked dependencies, licence compliance and security risks introduced through AI coding assistants. The announcement has drawn attention in software security and supply chain circles.

Linus Torvalds, creator of Linux and a longtime AI skeptic, has reportedly used an AI tool to help fix a bug in the kernel. The report from XDA Developers frames it as a telling moment: critics of AI-generated code in open source now face a choice between their stance on the technology and the practice of Linux's own founder. Discussions are circulating among developers on Mastodon and other forums.

Open source cybersecurity is struggling with artificial intelligence: attackers can use AI tools to find vulnerabilities faster and generate malicious code, while defenders are turning to the same technology to detect threats and patch weaknesses. Analysts argue the same capabilities cutting both ways make AI an unavoidable part of securing open source software.

Developers and AI commentators are discussing the distinction between retrieval-augmented generation (RAG) and AI agents, two approaches for extending large language models beyond simple question answering. RAG grounds model output in retrieved documents, while agents can plan and take multi-step actions. The conversation forms part of ongoing debate in the software community over how best to build practical applications on top of LLMs.

Software supply chain security firm Insignary has launched Clarity AIR, a new tool designed to identify undeclared open-source components and code generated by AI in software projects. The announcement has been picked up across multiple technology and cybersecurity outlets. The product targets a growing compliance concern: development teams increasingly use AI assistants and open-source libraries without documenting them, creating security and licensing risks for companies.

Microsoft has made MXC available on GitHub, describing it as a sandboxed code execution system. The project lets code run in isolated environments, a capability in demand for safely running AI-generated or untrusted programs. Developers on Hacker News have been sharing and discussing the release, examining its approach to isolation and how it compares with existing sandboxing tools.

A new finding suggests AI coding agents perform just as well when they skip writing their own tests, challenging a common assumption that test generation is key to their effectiveness. Developers are debating what this means for how automated coding tools should be evaluated and used in real-world software projects.

Open-source alternatives to Adobe Photoshop, Premiere and Illustrator built with AI assistance are now available, according to tech news coverage. The tools recreate the core functionality of Adobe's flagship creative software without licensing fees. The development highlights growing interest in free alternatives amid Adobe subscription costs and AI-generated code lowering barriers for building complex software.

An AI developer is making headlines after declaring that traditional software is effectively over, and is building open source alternatives that replicate Adobe's flagship creative tools. The claim has sparked debate in tech circles about whether AI-generated code can realistically replace commercial software suites, and what that would mean for Adobe's business model and the creative industry at large.

A new tutorial walks WordPress site owners through adding AI-generated music to their sites using free APIs. It covers why automated music matters for websites, how to pick a suitable free API, and a do-it-yourself integration built step by step, starting with securing an API key and writing the code, with a focus on a setup that can scale.

Developer jjak82 has launched StayLeet, a tool aimed at helping programmers keep their coding skills sharp as AI assistants increasingly write much of the code. The project was shared on Hacker News, where readers are debating whether practicing algorithmic problems still matters when AI can generate solutions on demand.

Microsoft has made its Execution Containers (MXC) generally available, offering policy-driven containment for AI agents, generated code, plugins and tools across Windows, macOS and Linux. The technology is MIT licensed. The core idea is that an agent cannot act as its own security authority: developers and IT teams declare which files and resources the agent may access, enforcing boundaries from the outside.

A question is circulating among developers: when code is written, reviewed and shipped entirely by AI and a bug slips through, who bears responsibility? The debate touches on the practice of 'vibe coding', where programmers rely heavily on AI generation with limited human oversight. Commenters are weighing accountability for engineers, teams and companies as AI takes over more of the software development pipeline.

A new five-axis code review checklist is being shared for teams working with AI coding agents. The argument: these agents produce fluent, syntactically clean code that compiles on the first attempt, but surface-level quality can hide deeper design and correctness problems. The checklist aims to give reviewers a structured way to assess AI-generated code beyond whether it simply builds and runs.