Sometimes You Have to Delete Everything

大家好，周日快乐！Vibe Checks 总是充满了意想不到的曲折和转折。在我们与 Anthropic 团队合作测试曾经的 Opus 5 时，截止日期发生了变化，发布候选版本也在调整，而模型则不断与我们为早期 Claude 版本建立的设置作斗争。这既让人疲惫，又让人兴奋。所以，当 Every New York 团队的一些成员在模型发布前一天早晨观看了《奥德赛》时，我们并没有忽略其中的平行意义。向下滚动可以查看完整的 Vibe Check 以及我们本周发布的其他内容。—— Kate Lee

“Claude Opus 5 时而出色，实践中令人沮丧”——作者：Dan Shipper 与 Katie Parrott / Vibe Check：Claude Opus 5 时而出色，实践中令人沮丧——它可以构建强大的软件并连续数小时处理漏洞，但其最佳表现往往需要拆掉你已经依赖的系统。它未能达到 Fable 的高度，也无法与 GPT-5.6 Sol 的日常易用性相比。阅读本文可帮助你决定 Opus 5 是否值得腾出空间——以及为了充分利用它，你需要做出哪些改变。

“Every 团队如何利用 AI 推出其最大规模的上线项目”——作者：Laura Entis / Context Window：我们的 All Access 上线带来了公司历史上最大的收入增长——大约两天内获得 9,000 美元。Every 首席运营官 Brandon Gell 将话筒交给三位同事——创下收入纪录的 All Access 上线背后的建设者——增长工程师 Yash Poojary、增长负责人 Austin Tedesco 和市场负责人 Douglas Brundage——讲述他们构建工具的方式以及给初学者的建议。观看或收听，了解一个 AI 原生团队如何将创意变为实际发布的产品。 🎧 🖥 可在 Spotify 或 Apple Podcasts 收听，YouTube 上观看，或在 X 上关注讨论。内容还包括：OpenAI 的 Romain Huet 和 Dominik Kundel 分享使用 Codex 的入门攻略，Marcus Moretti 通过委派给更廉价的子代理减少 Fable 的代币消耗，以及“每日驱动”，记录团队本周使用的模型列表首次亮相。

“为什么有些 AI 工作流程能坚持下去，而有些不能” —— 凯蒂·帕罗特 / 加班工作 : 在放弃了一个 Dan 的 Tend 的“注意力桌面”克隆后，凯蒂不再把它视为个人失败，并对为什么有些 AI 工作流程能坚持下去而有些不能进行了事后分析。她发现，一个工作流程的存活或失败取决于它对你的时间、精力和心理健康的要求与它所回报的相比如何。阅读本文，可以了解她用来决定哪些工作流程应保留、重新设计、重新审视或废弃的四个问题。

Every 的每个成员都在 AI 的前沿生活和工作。立即加入。

享受对 Every 所有内容的无限访问。

Hello, and happy Sunday! Vibe Checks are always a journey filled with unexpected twists and turns. As we worked with the Anthropic team to test what was Opus 5 , deadlines shifted, release candidates changed, and the model kept fighting the setups we’d built for earlier versions of Claude. It’s exhausting and exhilarating. So when some of the Every New York team caught The Odyssey the morning before the model launch, the parallel wasn’t lost on us. Scroll down for the full Vibe Check and everything else we published this week.— Kate Lee

“Claude Opus 5 Is Brilliant in Flashes, Frustrating in Practice” by Dan Shipper and Katie Parrott / Vibe Check : Claude Opus 5 is brilliant in flashes and frustrating in practice—it builds strong software and grinds through bugs for hours, but its best work often requires tearing down the systems you already rely on. It doesn’t reach Fable ’s ceiling or match GPT-5.6 Sol’s day-to-day ease. Read this to decide whether Opus 5 is worth making room for—and what you’d have to change to use it well.

“How Every’s Team Used AI to Ship Its Biggest Launch Ever” by Laura Entis / Context Window : Our All Access launch drove the biggest revenue gain in company history—roughly $9,000 in two days. Every COO Brandon Gell hands the mic to three of our colleagues the builders behind the record-setting All Access launch—growth engineer Yash Poojary , head of growth Austin Tedesco , and head of marketing Douglas Brundage —to walk through the tools they build with and their advice for anyone starting out. Watch or listen to learn how an AI-native team turns ideas into shipped products. 🎧 🖥 Listen on Spotify or Apple Podcasts , watch on YouTube , or follow the discussion on X . Also inside: OpenAI’s Romain Huet and Dominik Kundel share a playbook for getting started with Codex, Marcus Moretti cuts Fable’s token spend by delegating to a cheaper sub-agent, and “the daily driver,” a running list of the models the team is using this week, debuts.

“Why Some AI Workflows Stick—And Others Don’t” by Katie Parrott / Working Overtime : After abandoning an “Attention Desk” clone of Dan’s Tend , Katie stopped treating it as a personal failing and ran a post-mortem on why some AI workflows stick and others don’t. She found that a workflow survives or dies on what it asks of your time, energy, and sanity versus what it gives back. Read this to get the four questions she uses to decide which workflows to keep, redesign, revisit, or retire.

Every members live and work at the edge of AI. Join now.

Enjoy unlimited access to all of Every.