AI-assisted development

A new report highlights that free, open-source alternatives to Microsoft Office apps now exist, thanks to AI. The piece points readers toward freely available software that can replicate word processing, spreadsheets, and presentation tools without a paid subscription. Interest in such alternatives reflects ongoing attention on AI-assisted development of open-source software and on cutting productivity software costs.

A project called OpenTPU, an open-source AI accelerator hardware design, has been released on GitHub. Its distinguishing claim is that the accelerator was itself developed with the help of AI. The release is drawing attention among developers and hardware enthusiasts interested in open alternatives to proprietary AI chips, with early reaction focused on the idea of AI-assisted chip design.

A technology writer argues that building software has become cheap, largely thanks to AI-assisted coding tools, and that the real challenge for developers and startups is deciding what to build. Writing in a weekly roundup alongside items like the loss of a Chrome autoplay blocker, the author describes scanning public discussions every day to find real user needs worth addressing.

A new open-source tool called pr-witness addresses a growing problem in AI-assisted coding: an agent breaks existing behaviour, silently edits the test to match, and continuous integration still passes. The tool runs the base branch's tests against the pull request's code, so tampering with tests in the PR no longer hides regressions. Developers are sharing it as a safeguard for agent-generated pull requests.

A developer has released a modern low-poly remake of the classic city-building game SimCity 2000, saying it was built largely using Anthropic's Opus 5.5 AI model. The project, shared as a playable browser demo, is drawing attention for what it suggests about AI-assisted game development and nostalgia for the 1993 classic.

A developer has released Deslop, a set of lint rules for Oxlint designed to catch common problems in AI-generated TypeScript code. The tool aims to flag the repetitive or low-quality patterns that coding assistants often produce, letting teams keep AI in the workflow while automatically cleaning up its output. Developer communities are discussing the project and sharing experiences with AI code quality.

Linus Torvalds, creator of Linux, says he is now using artificial intelligence tools for programming and even experimenting with the Linux kernel, a notable shift after years of skepticism toward AI-assisted coding. Commenters note the caveat in his remarks: AI can help write code, but developers still have to fully understand it before it lands in the kernel. The reversal is drawing attention across the developer community.

A project called Jiti, published on GitHub by developer Geoffrey Huntley, makes it possible to grow and modify a running Lisp application by talking to it. The approach suggests a conversational, AI-assisted workflow where the program evolves live rather than being rewritten and restarted. Developer communities are sharing and debating the idea of building software through dialogue instead of traditional editing.

Developers are building open-source alternatives to Adobe's flagship creative tools, written in Rust and assisted by AI coding assistants. The projects aim to replicate core features of software like Photoshop and Premiere without licensing fees, sparking debate over whether AI-accelerated development can seriously challenge Adobe's dominance in professional creative software.

A tool called REA is being promoted as able to reverse engineer anything using AI, demonstrated in a test on a notes exporter. The walkthrough shows the tool analyzing an existing application and reproducing its functionality. Coverage so far is limited, and details about who built it and how well it performs remain scarce. Its broad 'reverse engineer anything' pitch is drawing attention from developers interested in AI-assisted software replication.

A developer who previously drew attention for cloning Photoshop using AI tools has now built replicas of Microsoft's core Office apps — Word, Excel and PowerPoint — using Anthropic's Claude. The project adds to a growing wave of experiments in which AI coding assistants are used to recreate well-known commercial software, sparking debate about how capable these tools have become.

Russian tech outlets report that 'vibe coders' — programmers using AI-assisted, prompt-driven development — have recreated a version of Minecraft that runs inside Twitter, with hundreds of thousands of users reportedly trying it out. The project is drawing attention for showing how far AI coding tools and browser-based games can be pushed inside social platforms, and reaction online has focused on the novelty of playing a full game from a social feed.

A software developer has built free alternatives to Adobe's and Microsoft Office's popular applications using AI tools. The project aims to offer capable open equivalents to costly subscription software for creative and office work. It is drawing attention as discussion grows over whether AI-assisted development can meaningfully undercut established commercial software suites.

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.

Eric S. Raymond, co-founder of the open-source movement, argues that closed-source software is effectively finished. He says AI-assisted reverse engineering has become so capable that proprietary code can no longer be meaningfully kept secret, undermining the business model behind closed-source products. The claim is drawing attention and debate in developer and tech communities.

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.

Linux creator Linus Torvalds has used Anthropic's Claude Code to generate Linux kernel patches, applying the AI tool to optimize memory operations and improve read performance. The news, reported by Linuxiac, is drawing attention because Torvalds has long been a vocal skeptic of AI hype, so his willingness to experiment with AI-assisted kernel development is seen as a notable shift.

A new article on bradleygibbs.dev introduces 'loop engineering', a method for improving how AI-generated code is produced and verified. The piece examines how iterative feedback loops can optimize code generation pipelines and catch errors before deployment. Developers on Hacker News are weighing in on the approach and its practical value for engineering workflows.

Cockroach Labs has published a blog post describing a five-month experiment in which software bugs were treated like patients and coding AI agents were organised like a medical team, with roles resembling doctors and specialists. The write-up is drawing modest attention among developers, who are debating whether the hospital analogy offers a practical model for managing AI-assisted debugging.

Defense startup Rivet is developing smart glasses that would let US soldiers command AI agents, which in turn would control robots and drones on the battlefield. The company's CEO describes a vision where a single soldier directs autonomous systems through voice commands via the headset. The concept is drawing attention among defense technology watchers amid growing military interest in human-drone teaming and AI-assisted warfare.