A developer with a Ph.D. in Instrumentation Physics confesses that the website’s engine was built almost entirely by AI agents, while the site content itself was not AI-generated. After a career shift from science to hands-on software work across Perl, PHP, Python, Node and Kubernetes, the developer encountered a turning point in spring 2026 when multi-agent workflows began to reliably build, test and review code against concrete requirements. That agentic approach overcame typical AI hallucinations by using testable, iterative development. Pressing time constraints led to a hands-off experiment: specify features, let agents implement them, and avoid editing the code directly. The result includes ambitious features the developer wouldn’t have coded alone - a tag engine with a query language (examples: single-element+!index, index+!single-element), an interactive Timeline, and the companion FigureShift tooling - all produced with minimal human coding.
The developer is torn: the site works and enables richer functionality, but the joy of craftsmanship is gone. Human involvement is still required for high-level ideas, steering, and pruning agentic tangents, yet most implementation credit and learning were bypassed. Ethical objections loom large: reliance on uncredited open-source work, training on public (and possibly private) code, and shrinking opportunities for paid freelance development and maintainers. The conclusion is conflicted pride and remorse - effective results paired with unease about how they were produced, and a hope for accountability even as the author admits to using the same tools to keep up.
Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.
Vibe Coding Production Kit is a workflow designed for developing AI coding agents, streamlining the process from issue identification to code deployment. It integrates with tools like GitHub Copilot and offers resources for developers working on AI-powered software development. (github.com)
SkillOpt treats natural-language skills as trainable external artifacts for frozen agents, optimizing them through rollouts, reflection, and validation. It improves agent performance by making the skill document itself the target of structured edits, avoiding fine-tuning of the underlying model. (microsoft.github.io)
Opus 5.5 can generate explainer videos automatically using a serverless agent on OpenComputer, taking a URL or prompt to produce a video in about four minutes. It leverages a microVM environment, web tools, and a deterministic rendering process to create high-quality videos without manual editing. (launchvideo.io)
Anthropic has signed a $12 billion agreement with Akamai to access AI computing resources. The deal aims to support Anthropic's development of advanced artificial intelligence models. (bloomberg.com)
Tech leaders from major AI companies have urged the United Nations Security Council to regulate artificial intelligence technology to prevent potential threats to humanity. They warn that unchecked AI development could pose significant risks to global safety. (apnews.com)
GPT-6 Sol shows significant performance degradation compared to previous models, with lower test scores and many hidden bugs. GPT-6 Luna performs even worse, indicating a decline in quality for the new release. (twitter.com)
Today's best Hacker News stories, summarized and screenshotted, one email a day.