Morning Brew co-founder Alex Lieberman built a six-step Claude content machine that generates publishable posts without producing generic AI slop, using an Oracle to scan for content spikes, an interv…
Claire explains that a harness is code written around an AI agent to make it more effective at a specific job, and she walks through the custom Claude Agent SDK harness she built to automate Sentry bu…
Claire Vo, founder of ChatPRD and host of the How I AI podcast, conducted a head-to-head comparison between OpenAI's GPT-5.6 lineup and Anthropic's Claude models, finding that the theoretically superi…
OpenAI's GPT-5.6 Sol outperformed GPT-5.6 Terra, Luna, Claude Fable 5, and Sonnet 5 on Claire Vo's custom benchmark across PRDs, prototypes, wireframes, debugging, and agentic voice tasks. Sol also de…
GLM 5.2, an open-weight coding model from Z.AI, outperformed Claude Opus in four real-world coding tasks including a codebase audit, UI redesign, and autonomous bug hunting, costing only $3.36 for 6 m…
Claire Vo breaks down four types of AI agent loops—heartbeat, cron, hook, and goal—and demonstrates live builds of a daily aging-PR reviewer in Claude Code and a weekly skills-identification loop in C…
WorkOS hosted MCP Night: Agent Mode in San Francisco, where founder Michael Grinich announced auth.md, a new product enabling agents to register for services on behalf of users. The event featured lig…
Fin, a customer service platform, tripled its research and development output within 16 months by forming a dedicated, autonomous core team of senior engineers and making it every employee's job to co…