taste

Emil Kowalski argues that as AI makes functional software abundant, product differentiation shifts to taste — a trained instinct built by studying great work, analyzing why things feel good, and practicing relentlessly with feedback.

A translated and compiled article outlining ten principles of good design from Paul Graham's 'Taste for Makers,' including simplicity, standing the test of time, solving the right problem, leaving room, humor, hard work, seeming effortless, symmetry, learning from nature, and constant revision.

The article discusses how taste in creativity originates from personal practice and experience, critiquing the reliance on generative AI tools and the trend of valuing taste over hands-on work.

The article discusses the concept of taste in AI and software engineering, suggesting that as AI handles mechanical tasks, human judgment and aesthetics become more important, with references to Andrej Karpathy, Rick Rubin, and Richard Hamming.

An essay arguing that as AI collapses the cost of software production, taste—the wordless verdict of quality—becomes the decisive skill for developers.

Addy Osmani reflects on the role of taste and judgment in an AI-driven world, arguing that while AI can acquire taste, human judgment—rooted in accountability and ownership—remains irreplaceable.

A guide to building 'taste' for AI agents like Hermes, OpenClaw, and Claude Code using Garry Tan's Gbrain framework.

Harvard professor Matthew Schwartz published an article on the Anthropic blog demonstrating using large language models like Claude, GPT, and Gemini to complete a quantum chromodynamics paper in two weeks (normally taking a year), and highlighted the strengths and weaknesses of LLMs in research. The author further proposed engineering fixes, including external computation modules, verification agents, and human oversight, emphasizing using LLMs as the core engine of scientific research.

The article discusses how AI automation will make most high-income skills obsolete. It proposes four core skills needed in the future: initiative, taste and unique perspective, judgment, and deep generalism. It emphasizes that humans need to actively adapt to become 'sovereign individuals'.

The author argues that the key question about AI-generated content should not be 'did AI write this?' but rather what human judgment and taste were applied before output, emphasizing the need for context, evidence, and editorial decision-making.

An essay exploring the concept of 'taste' as the ability to make high-quality qualitative judgments, arguing that taste becomes more valuable as production is commoditized by AI.

A thread arguing that 'taste' in software development is not mystical but simply an unarticulated evaluation framework, and that what you choose to measure defines your standards.

moop is a social network centered around taste, launched on Product Hunt.

A thoughtful thread on developing genuine research skills in machine learning, covering how to pick problems independently, cultivate taste, upgrade information inputs, and write to clarify thinking.