MikeTrendsTrends right now
AI: reposAPI

search

AI code generation

Trends

  1. 1
    Dermatologist launches 3D biophysical skin model built with AI coding●Show HN: I'm a dermatologist and I vibe coded a 3D biophysical skin modelYhnWorldHuman Rights91 h ago

    A dermatologist has released an interactive 3D biophysical model of human skin, built using AI-assisted coding despite having no formal software background. The project is drawing attention among developers and medical professionals as an example of how vibe coding lets domain experts build specialised tools themselves, sparking discussion about the quality and accuracy of AI-generated scientific software.

  2. 2
    New 'Impeccable' project aims to improve AI design skills●pbakaus/impeccable⬢github1.2K10 min ago

    Developer Paul Bakaus released Impeccable, an open-source JavaScript project described as a design language that makes AI coding assistants better at design. The repository quickly drew attention, ranking among the most discussed JavaScript projects on GitHub. Early reactions focus on whether giving AI tools explicit design guidelines can noticeably improve the visual quality of what they generate.

  3. 3
    Ponytail tool makes AI agents code like lazy senior devs▼DietrichGebert/ponytail⬢github1.9K10 min ago

    A developer has released Ponytail, an open-source JavaScript tool designed to make AI coding agents behave like 'the laziest senior dev in the room'. Its guiding principle is that the best code is the code you never wrote, encouraging agents to avoid unnecessary additions and favour minimal solutions. The project is drawing attention among developers experimenting with AI-assisted programming, who are debating how to curb over-engineering by code-generating assistants.

  4. 4
    Hackers Ask: Is Anyone Producing Good Code With AI Agents?●Ask HN: Is anybody producing good code with coding agents?YhnScienceBiology2826 min ago

    A question on Hacker News asks whether developers are actually producing good code with coding agents like AI assistants that write code autonomously. The poster, ruffrey, wants concrete examples of success rather than hype. The discussion, which drew modest engagement, touches a live nerve in software engineering as teams weigh productivity gains against quality and review overhead from AI-generated code.

  5. 5
    Greg Kroah-Hartman discusses security in the LLM age●Greg Kroah-Hartman – Security in the LLM Age [video]YhnTechnologyAI33339 min ago

    A recorded talk by Greg Kroah-Hartman, a longtime Linux kernel maintainer, examines how large language models affect software security, particularly for open-source kernel development. The talk explores what security maintainers need to consider as AI-generated code becomes more common. Readers are engaging with the discussion, which taps into ongoing debate about AI's role in critical infrastructure code.

  6. 6
    Startup says its vibe-coded website looks professionally designed●How our vibe coded website looks like a designer made itYhnTechnologyInternet13735 min ago

    RailCode has published a blog post claiming its website, built entirely through vibe coding with AI tools, turned out polished enough to pass as the work of a professional designer. The team walks through how the site was assembled, arguing that AI-assisted development can now produce visually credible front ends without hiring designers.

  7. 7
    Vibe Coding Lets Developers Build Fast with AI Guidance●𝕏xSE5912 h ago

    Developers are embracing 'vibe coding', a practice of building software quickly by describing what they want in plain language and letting AI tools generate the code. Supporters say it dramatically speeds up prototyping and lowers the barrier for non-programmers. Critics warn it can produce untested, poorly understood code and may create maintenance and security problems as projects grow.

  8. 8
    One Language, One Framework: Rethinking How We Learn to Code with AI●1 Language 1 Framework | The New Age of Learning Development with AI▶youtubeTechnologySoftware240.9K1 h ago

    Developers are debating a simplified approach to learning software development in the age of AI: mastering just one programming language and one framework instead of spreading across many tools. Supporters argue that AI assistants now fill knowledge gaps, letting beginners build real projects faster with a narrower stack, while the debate raises questions about whether deep fundamentals still matter when AI can generate code on demand.

  9. 9
    Open-Slide 2.0 lets coding agents build your presentations●open-slide 2.0 : un framework pour générer vos présentations en laissant votre coding agent écrire le React, pendant queMmastodonTechnologySoftware51 h ago

    Developer Camille Roux has released Open-Slide 2.0, a framework for generating presentations in which an AI coding agent writes the React code while the tool handles canvas rendering, navigation and hot reload. The framework exports editable PPTX files, static HTML or PDF, runs without a server and avoids vendor lock-in. It is being shared among developers interested in AI-assisted workflows as a fresh alternative to traditional slide software.

  10. 10
    AI-generated Taipei GTA clone draws 1.2 million players●Free browser-based AI-generated Taipei GTA clone hits 1.2 million concurrent players in three days — vibe-coded game cost $10,000 in AI tokens to build, is set on the streets of Taipei✉newsCultureGaming2 h ago

    A free browser-based game built almost entirely with AI coding tools has reached 1.2 million concurrent players within three days of launch. Described as a GTA-style clone, it is set on the streets of Taipei and reportedly cost around $10,000 in AI tokens to create. The speed of its rise and its low build cost are fueling debate about AI-made games.

Repos