Skip to content

#教程/实践

4 today

Today · Nov 17Tuesday · 4 items

Hacker News front page

My Quest to push native Three.js quality match AAA Game Engines

一份进展报告逐阶段对照 AAA 游戏引擎需求,梳理 Three.js 渲染管线现状:G-buffer、烘焙 GI、GTAO、随机 GGX SSR、SSGINode、TRAA/TAAU 等已落地或在评审中,最大缺口集中在 SSR 的 Hi-Z tracing 与 coverage、SSGI coverage,以及把两级级联接入 BRDF 的可插拔间接光照。

OpenAI News

At Holiday Extras, dots get to work before anyone asks

Holiday Extras 员工使用 dots 主动生成产品上线报告、提醒潜在问题,并通过语音讨论即将举行的会议。AI 创新副总裁 Liam Thompson 的 dot 从 Google BigQuery 获取数据后主动提交报告;同事 David Lee 的 dot 在 API 密钥需要停用时检索邮件,列出可能受影响的人。

claude.dev Blog

How the Claude Code team verifies code written by AI

About 90% of the Claude Code team's code is written and reviewed by Claude, with changes verified by running the real app, automated checks and human review. The team describes end-to-end, property and differential testing, and a verify skill that hands a change to a person after three failed check rounds. Review rules are read from the base or default branch so a change can't edit its own checks.

Why it matters: The team folds end-to-end verification, escalation to humans and isolated review rules into its workflow, replacing line-by-line reading with defined done criteria and review evidence.

Hacker News front page

A 512 KiB binary message teaching chess without a shared language

Artem Legotin 发布 Golden Board 项目,用 4,194,304 位(512 KiB)的二进制消息向没有共同语言、文化或棋类知识的接收者教授国际象棋。消息前 64 行含 32 幅 64×64 图像构成引导层,先教会如何读取自身内容,下方载荷包含可视化课程、带反馈练习和完整对局。作者用 LLM 模拟未知接收者测试解码与理解,代码和文档已在 GitHub 开源。

Yesterday · Nov 16Monday

Hacker News front page

Interpreting claims that a theorem is correct because it was checked in Lean

Lean 检查能为定理正确性提供重要依据,但 AI 生成的代码还需核验命题对应关系、编译结果、所用公理及内核可靠性。文章介绍了用 lake comparator 检查命题一致性与公理、用 lake comparator --paranoid 进行多内核复核的方法,并指出 OpenAI 附带 Lean 代码的 290 篇论文中,约 38 篇的代码未陈述论文的主要定理。

Hacker News front page

How to make almost anything

MIT「How to Make Almost Anything」课程公布 2026 秋季日程,将 AI agents 与 Edge AI 纳入教学:10/01 的 3D 扫描与打印课辅以 AI agents 讲座,10/29 的输入设备课配 Edge AI 幻灯片与代码。课程还覆盖 CAD、嵌入式编程、电子设计与生产、CAM、网络与通信等,12/15 进行期末展示与 open house。

The Decoder

Anthropic's Claude Fable 5.2 doesn't generate images, it paints them

Anthropic 的 Claude Fable 5.2 能用代码在虚拟画布上逐笔作画,模拟笔刷纹理、颜料覆盖和失误修正。Anthropic 开发者 Jake Eaton 展示的停车场购物车画作使用约 700,000 次模拟笔触,据他介绍,每幅作品由 1,000 至 2,000 行 Python 程序驱动画具模拟引擎,不使用外部图像模型或预渲染、描摹的源图像。

Nov 15Sunday

Hacker News front page

Semicircle Packing

Paradigm 官网 Puzzles 页上线“Pack Semicircles”谜题,要求把 15 个相同半圆排成尽可能紧凑的布局,使外接圆最小,并配有公开排行榜。作者用 Affinity Designer 的 Symbols 工具手动尝试对称排布,把外接圆半径设为 3 时已能进入排行榜前 2/3。该谜题可用 X.com 账号登录提交解答。

The Decoder

Anthropic says outdated prompting habits slow Claude Opus 5.5

Anthropic advises Claude Opus 5.5 users to drop phrases like "think hard" and start at the default Medium reasoning effort. In internal tests, removing such wording made responses start faster with no measurable quality drop, and Opus 5.5 at Medium matched Opus 5 at High. Other tips: state the goal, output format and when to ask follow-ups in one go, attach charts or files directly, and name unwanted design styles.

Why it matters: Anthropic's guidance boils down to stating a clear endpoint, cutting prompts that push the model to think harder, and raising reasoning effort only when needed.

Hacker News front page

A visual explanation of reinforcement learning

一篇交互式可视化文章用只有四个神经元、三个可调参数的虚拟生物 spark 演示强化学习:随机微调脑内连接,表现变好就沿该方向调整、变差则反向调整。spark 从随机接线时原地打转,经 50 次尝试开始移动、250 次学会避光、500 次冲向光源、2000 次成为追光专家。文章把这一过程画成“大脑参数空间”中的学习路径,显示数百个初始接线不同的个体最终都收敛到同一目标。

Nov 14Saturday

Computing Life · Share · Yage

微软邮箱故障为何拖累办公软件与三大 AI 助手超过 26 小时?

微软云端邮箱故障持续超过 26 小时,波及办公软件及 Copilot、Claude、ChatGPT 获取企业资料的功能。网络配置变更触发潜伏缺陷,安全核验程序过载与客户端自动重连使恢复受阻,团队通过扩容、限流、修补组件和逐步恢复连接处理故障。邮件、日历及权限服务的共同依赖让多家 AI 助手连接器同时受影响,微软通报称故障与 AI 智能体无关。

Nov 13Friday

Hacker News front page

Reverse Engineering My Coway Air Purifier to Ditch the Cloud

一位用户通过中间人(MitM)方式逆向工程 Coway Airmega IconS 空气净化器,试图让它脱离 Coway 云服务、改由本地控制。此前 Home Assistant 的 IoCare 集成只能模拟手机 App 轮询云端,每年会因封禁、App 改版、HTML 布局变动或服务器离线而失效一两次。

Computing Life · Share · Yage

Why nearly half of leaked configs were committed to GitHub by Claude Code itself

Claude Code's "don't ask again" option writes commands containing plaintext credentials into .claude/settings.local.json. Apiiro found that 48.8% of traceable leaking repos had that config uploaded by commits signed with Claude.

Why it matters: Claude Code saves approved commands, passwords included, to a local config, so project-level ignore rules and env-var injection cut the credential exposure when that config gets committed.

OpenAI News

Gondola doubles revenue as its team builds more with Codex

Gondola 使用 Codex 后,团队月度工程产出提高约 25%,公司营收同比增长超过 2 倍,未增加薪资成本或显著开销。业务团队用 Codex Cloud 制作可运行原型,再交由工程师完善上线;首席工程师按合并代码变更衡量的月度产出提高约 50%,工程团队人数未变。团队还用 ChatGPT 准备提案、管理日程和汇总跨系统信息,重要工作在对外发送或用于业务决策前仍由人工审核。

OpenAI News

Amplitude cuts product improvement delivery to 1–2 days with OpenAI models

Amplitude estimates its product agent Wave, driven mainly by OpenAI models, can cut product improvement delivery from about a month to 1–2 days. Wave combines product data, session replays, customer feedback and code to spot opportunities, drafts technical plans and acceptance criteria, then hands them to coding agents including Codex to implement, and tracks results. Teams set the level of automation and how much human review applies.

Why it matters: Amplitude links data investigation, coding and outcome measurement, assigning models and human review per task so product improvement keeps both cost and team control in view.

GitHub Blog · AI & ML

Build once, run on any agent: A practical guide to agent skills

GitHub 以 Data Forge 和 Proof Agent 为例,讲解如何编写、组合与打包可跨智能体复用的技能。技能以 SKILL.md 为核心,将项目配置放入独立 manifest,并生成适用于 Claude Code、Cursor 和 GitHub Copilot 的客户端文件,工具、凭据和权限仍由运行环境提供。

OpenAI News

How Amplitude ships product improvements in 1–2 days with OpenAI

Amplitude 估计,其主要由 OpenAI 模型驱动的产品智能体 Wave 可将产品改进交付时间从约一个月缩短至 1–2 天。Wave 综合产品数据、会话回放、客户反馈和代码发现改进机会,生成技术方案与验收标准后交给包括 Codex 在内的编码智能体实施,团队可控制自动化程度。

Hacker News front page

Turning a 22-year-old Postgres type-confusion primitive into RCE

安全研究者将 PostgreSQL 核心中一个存在 22 年的类型混淆零日漏洞转化为高可靠性的内存破坏利用链,最终实现远程代码执行。该漏洞源于在复合类型字段中写入值后修改字段类型再读回,研究者在利用 pg_clickhouse 扩展时顺藤摸瓜发现,相关扩展漏洞已于 6 月 23 日修复。

Google Blog · Gemini

Get quick answers from Gemini on any website.

在 Chrome 工具栏点击 Gemini 图标即可打开侧边面板,无需切换标签页就能让 Gemini 总结冗长报告、对比产品细节或用通俗语言解释复杂话题,同时保持当前浏览位置不变。

Hacker News front page

AWS Lambda Web Functions keep billing memory ~7 minutes after the last request

Easel 实测 AWS Lambda Web Functions 发现,执行环境在最后一次请求后仍存活 313–411 秒并持续计收内存费用,且无空闲超时配置;内存约占其测算计算与请求成本的 88%。Easel 因此改为自建计算、仅用传统 Lambda 承接溢出流量,同一 Next.js 16 应用热请求中位延迟快 1.5–3×,闲置 12 分钟后冷启动快约 3.5×。

Computing Life · Share · Yage

Anthropic cuts request payload from about 800 KB to 1.8 KB, and why that doesn't clash with NVIDIA's long-context advice

Anthropic's Message Threads drops the median long-conversation request payload from about 800 KB to 1.8 KB by cutting repeated uploads, validation and tokenization. It does not reduce token consumption or the bill.

Why it matters: Anthropic trims gateway latency with incremental transfer while Nvidia trims decode cost with context compression, two routes for two different long-conversation costs.

Hacker News front page

Fitting Four 32 GB Resizable Bars Behind a PCIe Switch on Linux

一位开发者用 Broadcom PEX88096 PCIe 交换机在单 x16 插槽上接入四块 AMD Radeon AI PRO R9700 和两块 RTX 3090,并发布内核模块 gpu-rebar-layout,在 GPU 驱动加载前把每块 R9700 的 BAR 设为 32 GB 并重新扫描。

Nov 12Thursday

OpenAI News

Holiday Extras is rethinking what it can build with Codex

Holiday Extras 借助 Codex 在两周内完成可运行的应用重建,达到过去需要超过六个月的开发进度。重建后,主应用从打开到预订的转化率提升 32.5%,错误率从 19% 降至 9%;这些结果来自不同时间段的新旧应用比较。业务人员将客户与运营经验直接用于软件开发,工程师负责架构、API、安全控制和开发流程,主应用在重建后的第一个月由年度重大更新转为每周发布。

Computing Life · Share · Yage

代码中的旧 TODO 注释为何更容易让强模型编码智能体跑偏

Google 对超过 91.3 万次真实编码会话的研究发现,能力更强的模型更容易被源码中的旧 TODO 注释带偏。智能体擅自追踪历史注释时,单次对话平均多执行 70% 的步骤、多消耗 77% 的 token,等待时间增加 105%。

Hacker News front page

Lean Grimoire

作者用编码智能体重建了 2018 年的 Javascript 交互式逻辑教材“QED”,新版本暂定名“Lean Grimoire”,可展示当前游戏状态对应的 Lean 证明进度。应用还提供“fantasy mode”,把数学命题、表达式等元素替换为药水、卷轴等奇幻文本。作者希望获得试玩反馈,以提升其教授逻辑证明和 Lean 的效果。

Nov 11Wednesday

Latent Space

AI Engineer Code Summit: OpenAI on New Ways of Working With Codex

OpenAI 工程师在 AI Engineer Code Summit 演示了 Codex 的云端任务、语音控制和个人智能体 dots 工作方式。Codex Cloud 版本 2 支持发布一次环境后,在隔离实例中运行多个任务,但本地任务向云端交接仍涉及上下文差异,团队正在改进体验。语音可用于管理任务线程和委派工作,dots 则可提醒遗漏、承接委派,并利用已有上下文推进 PR。

Hacker News front page

An Open Field Guide to Inference Engineering

Modelplane 的推理工程指南面向平台工程师,系统讲解模型与 GPU 的配合、生产部署及职业学习路径。指南涵盖权重与 KV cache 显存预算、prefill 与 decode 瓶颈、引擎优化、网关鉴权、可观测性和扩缩容,并强调用真实流量开展并发评测。

Hacker News front page

Smart home devices should work without the internet

开发者 Spencer Kittleson 提出智能家居第一规则:核心设备断网也必须可用,其家中逻辑跑在 Tasmota 固件、MQTT broker 和树莓派上的 Node-RED 上。他因 Google 破坏 API 导致 Nest 集成失效、三星冰箱屏幕报 TLS 证书错误等问题,主张云服务只能作为附加项。他还要求云设备必须提供带日志的 API,否则不安装。

Nov 10Tuesday

Simon Willison

Yonkers Rises

Simon Willison 用 Claude Fable 5.2 Medium 生成了一段 three.js 动画:Yonkers 以大型机甲姿态站起,并踩踏曼哈顿、皇后区与布鲁克林,地图数据来自 OpenStreetMap。模型还正确推断出提示词中的 "átomos" 是手机键盘误打的 "stomps"。

Simon Willison

Anthropic doc: telling Claude Fable 5.2 it owns the codebase boosts duplicate-code merges

Anthropic's documentation says setting Claude Fable 5.2 as the code owner and long-term maintainer makes it more likely to merge duplicate code. In small coding tests, duplicate merges came in under 10 percent without that identity and around 75 percent with it. Simon Willison quotes the prompt as "you are the owner and long-term maintainer of this codebase, its design is yours to decide," and the model sometimes goes ahead and makes the fixes.

Why it matters: Anthropic's small coding test shows a code-owner identity prompt lifts Claude Fable 5.2's duplicate-code merge rate from under 10 percent to about 75 percent.

Computing Life · Share · Yage

如何用 gh skill 与 APM 管理 Agent 技能依赖和自动升级

Agent 技能依赖维护需要同步锁文件与实际技能文件,文章比较了 gh skill 和 APM + Dependabot 的方案与限制。Dependabot 调用 apm lock 更新账本,不同步已入库的技能文件且跳过安全扫描,对多行依赖配置、MCP 服务和私有源也存在支持限制。

Simon Willison

Locating the source of a mysterious beep with Claude

Simon Willison 用 Claude Code 构建 Beep Locator,通过多台设备监听和三角定位,将家中蜂鸣声的位置缩小到约 40cm 范围,找到了需要更换电池的旧一氧化碳探测器。

claude.dev Blog

Anthropic's Claude model guide: choosing between Fable, Opus, Sonnet and Haiku

Anthropic's selection guide says most coding and knowledge work should start with Claude Opus 5.5 at medium thinking effort, moving to Sonnet 5.5, Haiku 5.5 or Fable 5.2 as task difficulty changes. It frames model choice around the cost of finishing a task: set up automated acceptance checks first, then adjust thinking effort or step up a model, and hand easy-to-verify side tasks to smaller models.

Why it matters: Anthropic splits Claude selection into model, thinking effort and cost per finished task, and proposes automated acceptance checks plus reruns on failure to control spend.

Nov 9Monday

Simon Willison

Hide your slop PR descriptions behind

Simon Willison 用人工筛选的简短引言概括 PR 改动,再将 AI 智能体生成的完整描述放进 <details><summary> 折叠区。GitHub Markdown 支持这些 HTML 标签,他用模型名及思考力度标注折叠标题,例如 Claude Opus 5.5 Medium,并按需加入截图。