Keep on to blur preview images; turn off to show them clearly
it’s kinda obvious useful to think about for agent + harness —> progressive disclosure for skills disclosure is a feature of the harness, not the model the model didn’t choose to have all of the YAML frontmatter pre-loaded on its first turn the nice folks at Anthropic came up deterministically designed this pattern to help the model be better with context this mode of thinking is the recipe for good harness design basically what can we include something for the model (might be a subagent, a context management pattern, infra, etc) so that it can do better across the tasks we care about
leading deepagents and building evals @LangChainAI, prev @awscloud, phd cs @ temple
that infrastructure will go on to power american factories, american chip fabs, american refineries and smelters. the long years of energy stagnation will soon be over.
THANK YOU FOR YOUR ATTENTION TO THIS MATTER
This is a good example of why I started PortalVR. Many assume a non-HMD modality for VR will always be cumbersome or half an experience. They may be right, but generational companies are built on solving a problem by breaking big, wrong assumptions by working the problem hard.
Opening portals to VR without headsets at @portalvr_io. Problems soluble, potential to improve invariant.
没想到当时用在 Claude 的小红书封面前端提示词 现在用在 Nano Banana Pro 依然没啥问题！ 就不到十个月的时间，AI 发展真快啊
极简格栅主义封面风格
One of my America 250 projects is to read and study institutions that were truly built for scale, not companies. Nations, empires, the Holy Roman Catholic Church. You’d think there are many of these worth studying or understanding, but very rarely do builders think in time scales beyond their own lifetimes. It’s rare to actually start something with the belief it will outlast you, and to design an organization that makes you completely irrelevant to its long-term success. Anyway, accepting book recommendations!
Co-Founder, American Dynamism. General Partner @a16z. Catholic. Mother. American. 🇺🇸 🚀💪
RT @_krunalshah_: Well-designed agentic harnesses are underrated. Our biggest learnings building multi-agent orchestration for Scouts @yut…
Co-founder & Chief Scientist @yutori_ai. Prev: Senior Director leading FAIR Embodied AI @MetaAI and Professor @GeorgiaTech.