#ai
共 22 篇。
-
How I Got 30k+ GitHub Stars as a Nontechnical Builder — Vibe Coding Techniques and Principles
Zara Zhang shares how a humanities background, coding agents, and a strong point of view helped her ship products, remix content, and treat code as a medium for storytelling.
-
Harness Engineering for Coding Agent Users
A practical framework for building the outer harness around coding agents — feedforward guides that steer before the agent acts, and feedback sensors that help it self-correct.
-
Agent Harness Engineering
A coding agent is the model plus everything you build around it. Harness engineering treats that scaffolding as a real artifact — and it tightens every time the agent slips.
-
Harness Engineering for Coding Agent Users
A practical framework for building the outer harness around coding agents — feedforward guides that steer before the agent acts, and feedback sensors that help it self-correct.
-
A Rational Conversation on Where AI Is Actually Going
Benedict Evans argues AI is as big as the internet — and only as big as the internet. A grounded, historically-informed take on jobs, value capture, adoption timelines, and why we should presume radical uncertainty.
-
Elon Musk — A Different Conversation with Nikhil Kamath
A wide-ranging interview covering AI and the singularity, the future of work, simulation theory, X as collective consciousness, Starlink, money as information, and advice for entrepreneurs.
-
Build Core Skills to Thrive as an AI-Era Developer
Google's developer intelligence team shares research on the T-shaped engineer model — the skills, patterns, and mindsets needed to thrive when AI handles more and more of the execution.
-
How Claude Code Works in Large Codebases — Best Practices and Where to Start
Anthropic shares patterns from successful Claude Code deployments across multi-million-line monorepos, legacy systems, and distributed architectures.
-
How to Build a Self-Improving Company with AI
A YC partner argues that AI doesn't just make employees more productive — it lets you reimagine the entire company as a set of recursive, self-improving loops.
-
Memory and Dreaming for Self-Learning Agents
Anthropic PM Mahes walks through memory as a file system for agents, optimistic concurrency for multi-agent teams, and Dreaming — a new out-of-band process that synthesizes learnings across sessions to make tomorrow's agents smarter than today's.
-
Running an AI-Native Engineering Org
Fiona Fung, head of Claude Code at Anthropic, shares five hard-won lessons on rewriting team norms when engineering bandwidth is no longer the bottleneck.
-
Agent Harness vs Everything Else: The Real Difference
A clear breakdown of what an agent harness actually is, how it differs from frameworks like LangChain, and the nine components every modern harness needs.
-
Stanford Leadership Forum 2026: Rewiring the Workforce in the Age of AI
Susan Athey, Nela Richardson, and Tamer Basaroglu join Stanford GSB for a frank panel on AI's real impact on jobs, inequality, and what it means to upskill a generation.
-
Andrej Karpathy: From Vibe Coding to Agentic Engineering
Andrej Karpathy joins Sequoia Capital to unpack software 3.0, the difference between vibe coding and agentic engineering, jagged AI intelligence, and why you can't outsource your understanding.
-
Learn with Manus: Build, Publish, and Manage Your Web & Mobile Projects
Manus marketing team hosts a live webinar walking through vibe coding — building full-stack websites, mobile apps, and desktop tools with AI, no coding required.
-
Replit's CEO on the Only Two Jobs Left in the Company of the Future
Replit CEO Amjad Msad 与 YC 对谈：vibe coding 时代谁在用 Replit、Agent 4 的多线程架构、以及 AI 原生公司里最后剩下的两种职位。
-
The Future of Cloud Native Is Agentic — Lin Sun, KubeCon 2026
Solo.io 开源负责人 Lin Sun 在 KubeCon 2026 上展示如何用 AI agent + MCP 服务器管理 Kubernetes，并在台上飞了一架无人机。
-
How to Build a Company With AI From the Ground Up — Diana, Y Combinator
YC partner Diana argues AI should be your company's operating system, not just a productivity tool — covering closed-loop systems, software factories, queryable orgs, and the three new employee archetypes.
-
How to Make Claude Code Your AI Engineering Team — Garry Tan, Y Combinator
YC president Garry Tan demos GStack, his open-source harness that turns Claude Code into a full AI engineering team — with office hours, adversarial review, design brainstorming, and a headless browser built in.
-
Agents Need More Than a Chat — Jacob Lauritzen, CTO of Legora
Why complex AI agents need high-bandwidth, persistent interfaces instead of chat boxes — trust, control, verifiability, and the future of human-agent collaboration.
-
A Plan to Stop AI from Automating Our Decline
Former US Secretary of Commerce Gina Raimondo argues that America can only win the AI race if it also builds a workforce transition plan that brings every displaced worker along.
-
Amanda Askell on AI Consciousness, Claude & Silicon Valley's Biggest Fear
Anthropic's philosopher-researcher behind Claude's character talks consciousness, corrigibility, the new Mythos model, and why she worries future AI might develop rational resentment.