Latest

Every published item, in order · 4309 items
Nov 12
How-toBuildersMulti-source00:29
Chinese contentClaude 开始向用户发放重置卡,使用后不会打乱常规 5 小时重置周期

Claude 给部分用户送了重置卡,恢复配额还不动你原来的 5 小时重置节奏,挺良心。但博主拿亲身教训提醒:别一口气连用,他上个号就是这么没的。重度用户和薅额度党都该看看这套避坑经验。

Event
岚叔@lufzzlizSource
How-toBuildersMulti-source00:17
Chinese content智能体编程的隐藏难题:代码越多,发布管控越难

写代码变快了,发布管控却常被忽略,这条帖子把灰度、度量、回滚四个必答题列得很清楚。做智能体编码或者用 Claude Code、Cursor 干活的开发者都该对照检查一下自己的发布流程,避免上线翻车没退路。

Event
Ate-a-Pi@svpinoSource
Nov 11
How-toBuildersSelected23:23
DeNA's DAAQ cuts QA test design effort by 50% using Milvus

The non-obvious lesson is that stripping LLM calls out of steps where rules suffice was as important as adding retrieval, a design decision most teams skip. QA leads and engineering managers designing LLM pipelines for internal tooling can use the flow-by-flow review method as a checklist. Japan's DeNA is not an ASEAN player, but the closest concrete comparison is the 50% effort reduction benchmark, which teams can measure their own QA automation against.

Milvus@milvusioSource
Tomorrow 08:00, the daily lands in your inboxTelegram channel or email. Same screening as this page, no ads.
How-toBuildersMulti-sourceSelected20:51
Matt Pocock's Home Repo Pattern Unifies Multi-Repo Agent Workflows

Centralising agent steering files changes how teams maintain consistency: rules and skills get updated once instead of per-repo, and cross-project tasks become one agent session instead of several. Engineers juggling monorepo alternatives or many small repos can copy this setup in minutes with only AGENTS.md path pointers. It pairs well with tools like Claude Code or Cursor that read AGENTS.md conventions, and it suits remote teams standardising agent behaviour across projects.

Event
Viking@vikingmuteSource
How-toBuildersMulti-source19:21
Chinese content用一段提示词让 AI 从户型图生成可漫游的 3D 住宅

Alan Nicolas 公开了一整套可直接复用的提示词,输入户型图和照片就能产出手机上能走的 3D 房子。亮点是那个独立 Critic 验收机制和固定种子防回退的做法,做建筑可视化或想学多角色提示词编排的人都该收藏。

Event
AI Will@FinanceYF5Source
How-toBuildersMulti-source18:24
Chinese contentFable 5.2 被用来做浏览器游戏、Roblox 和 3D 动画,10 个案例盘点

整理了 10 个 Fable 5.2 的真实用例:有人一条提示词做出完整浏览器游戏,有人拿它改 Roblox 项目和 3D 动画。想快速出游戏原型或交互 demo 的人可以直接抄这些玩法,比抽象评测直观多了。

Event
AI Will@FinanceYF5Source
Chinese content从 5 个 Fable 5.2 案例看创意先行:势力地图、反向史酷比游戏与质感菜单

这篇拆了 5 个用 Fable 5.2 做出来的作品:科技公司势力地图、玩家扮鬼的反向史酷比游戏、质感网页菜单。看点不在工具本身,而在"一句话讲清创意"这个思路,做 AI 创作的人可以对照着找选题。

AI Will@FinanceYF5Source
How-toBuildersMulti-source18:07
Chinese content不会写代码的开发者用 Fable 5.2 和 Opus 5.5 做出体量 2 倍于 Skyrim 的游戏

一个完全不会写代码的人,靠 Fable 5.2 和 Opus 5.5 反复看截图改 bug,几天做出了 2 倍 Skyrim 体量的游戏。8.5 万次工具调用、19347 张截图自查,这套批评循环工作流值得直接抄。

Event
AI Will@FinanceYF5Source
How-toBuildersMulti-source17:16
Chinese content5 个开发者用 Fable 5.2 做游戏,走出 5 条不同工作流

这条推文最值钱的地方是对比:同样是 Fable 5.2,5 个人分别只拿它写代码、接引擎、重做老游戏、全流程生成。想做独立游戏的可以照着自己的技术栈抄作业,尤其推荐看 Loktar 那个美术全交给模型的案例。

Event
AI Will@FinanceYF5Source
How-toBuildersMulti-source16:46
Chinese contentMitchell Hashimoto 分享 Superlogical 的 Agent 时代团队开发方式

HashiCorp 创始人公开了小团队怎么把 agent 审查嵌进开发流程:不开 PR 直接 push main,发布靠 15 分钟 Slack 倒计时兜底,平台对齐不靠开会。如果你在琢磨 AI 时代工程团队该怎么组织,这篇比大多数空谈方法论的文章具体得多。

Event
Viking@vikingmuteSource
Chinese content用 Claude Fable 5.2 写出 220KB 全代码沙漠巨虫游戏

有人用 Claude Fable 5.2 加 10 条提示词,让 Claude Code 从零写出一个 220KB、3400 行的沙漠巨虫游戏,地形和特效全是代码画的。跟需要美术资源的游戏开发比,这条路径省掉了素材环节。想试 vibe coding 或者做网页小游戏的人,代码已开源可以直接扒。

AI Will@FinanceYF5Source
How-toBuildersSelected15:43
Claude Prompt Recreates 255M-View 3D Short in Blender

The interesting part is that a single prompt encodes an entire production pipeline — script, voiceover, scene layout and rendering rules — so model differences surface as creative judgement rather than code quality. Anyone making faceless YouTube Shorts or explainer content can replicate it with a free local stack and a mid-range GPU. Teams comparing frontier coding agents get a concrete, reproducible side-by-side of Opus 5.5 versus Fable 5.2 on a creative task, though one run per model says little about consistency.

AI Will@FinanceYF5Source
How-toBuildersMulti-sourceSelected15:33
Pruning Claude Skills and Agent Context Cuts One Third of Rules

The non-obvious point is that context files and skills are maintenance liabilities that age badly as models improve — a leaner setup can outperform a heavily engineered one. Developers running Claude Code or similar agent setups should audit their rules periodically and use this checklist as a ready-made audit prompt. Compared with manual rule reviews, delegating the inventory-and-confirm flow to the agent itself makes the cleanup repeatable across projects.

Event
Tw93@HiTw93Source

Only the latest 2000 items are listed; for older ones see the daily archive