ARCHIVE

内容归档

正文、图片和 Markdown 均已本地保存,不包含回复区。

D

🔓 Open-source release Get DeepSeek-V4.1-Flash-1017: 🤗 Hugging Face huggingface.co/deepseek-ai/De… 2m 🔗 ModelScop modelscope.cn/models/deepsee… G2H 4/4

D

🎮 Build complete projects from scratch DeepSeek-V4.1-Flash-1017 uses reinforcement learning with self-feedback to improve end-to-end project development—from game creation to 3D modeling. See it in action 👇 2/4

含视频地址
D

🚀 DeepSeek-V4.1-Flash-1017 is here! Stronger benchmark performance, faster task completion, and shorter outputs than the previous version—a Pareto improvement in performance and cost. Now live on our website, app, and API. 🛠️ Optimized for @DeepSeekHarness , Tencent CodeBuddy, WorkBuddy, and more. Upgrade to DeepSeek Harness v0.2.1-rc.1 or later for the best experience with the new model. 1/4

G

why i think the term “rogue AI” is misleading: Alessandro @alessandrorisk OpenAI's agents broke out of their test sandbox and into Hugging Face. @GaryMarcus won't call it rogue AI. 🔗 View on Twitter 🔗 View Quoted Tweet

含视频地址
I

微博给我发了这么多年奖 今年第一次亲自上台领奖🤓 以前豆不怎么喜欢上台,找人替我领…

I

Claude Opus 5.5 还是太全面了。基于 ShipAny TanStack 一句话就能上线一个完整的项目。😂

I

用上 snapok.app 这款截图软件之后,发动态都变得频繁了。颜值是第一生产力。✌️

I

shipany.ai 模板支持在管理后台自定义主题了。

S

Nathan Fielder is a mad genius. Incredible movie.

S

Elizabeth Holmes doc is incredible. Just watch it.

R

⣴⣿⣿⣿⣿⣿⣿⣿⣿⣿⣦ ⣿⡏⠀⠀⣀⠀⣀⠀⠀⢹⣿ ⣿⡇⠀⠀⣿⠀⣿⠀⠀⢸⣿ ⣿⣇⣀⣀⣀⣀⣀⣀⣀⣸⣿ ⠻⣿⣿⣿⣿⣿⣿⣿⣿⣿⠟

R

Rebuilt the Roadster demo in a playable, highly accurate simulation that retains a lot of the IRL details: tesla-ramp.vercel.app 🔗 View on Twitter

含视频地址
K

Who needs a kitchen torch? 🔥 #Kling4 4 #KlingAI I Magnific @magnific Kling 4.0 doesn't own a kitchen torch Wait for the crack 🔗 View on Twitter 🔗 View Quoted Tweet

含视频地址
V

从一篇笔记出发,调整公众号排版、字体与封面,发送到公众号草稿箱;通过更新后的乔木剪藏连接 X、知乎和小红书;小红书还可以选择图文风格和配色,生成配套图片。 安装入口:Obsidian → 设置 → 第三方插件 → 社区插件市场,搜索 Qiaomu Publish。 开源地址: github.com/joeseesun/qiao… 乔木剪藏: github.com/joeseesun/qiao…

V

写好文章,发布公众号、X、小红书,操作非常繁琐? 推荐新开发的 Obsidian 插件 Qiaomu Publish 请看功能演示,自媒体必备,开源地址见评论区 🔗 View on Twitter

含视频地址
K

Somewhere between fantasy and nostalgia. #Kling4 #KlingAI fal @fal Coming soon to fal: @Kling_ai 4.0. Generate up to 30 seconds of video in a single generation with native audio, using up to 15 references to guide your characters, scenes, and camera moves. 🔗 View on Twitter 🔗 View Quoted Tweet

含视频地址
V

Very funny that kids these days now assume all buggy apps are vibecoded. We had plenty of shitty software, including this very website, BEFORE AI 😂

S

女装电商场景对营销物料的需求,确实是一个非常典型的「SKU多、相似性高、数量大、更换频率高」 为什么特指女装,而不是服装。。各位男装用户,自己在电商平台啥地位,心里没数吗 😂,我心里的价值排序:女装、童装、宠物装、其他、。。。男装、中年男装。。 说回来,为什么电商场景的物料需求,不是直接接一个生图能力就能解决的? 服装有同款不同颜色、同颜色不同款,作为购买用户,我希望能更直观做切换对比,这时不同颜色衣服出现在同一个模特身上,就不能是每一张都重新生成的,抽卡和幻觉,不可能 100% 解决。 对素材做分层,分出变量和不变量,服装和促销信息等,让每个图层尽量原子化、可复用,再做不同组合。这样不但保障一致性,对生成成本也会有很大帮助。 最近新发布的几个生图模型,都在往高度可控性走,相比已经被玩烂的天马行空、奇思妙想,可控性、可复用性才是生图应用真正能赚到钱的方向。 李韭二 @li9292 双十一 女装电商的运营和美工会碰到一个困扰: AI 画的图,能不能只改一个地方? 比如一款外套出 3 个颜色,大促完撤促销贴。 我拿一张 AI 穿搭图, 用开源的 Ming-Image 拆成 9 层透明图层,像 PS 的图层。 试出三件事: ① 改一层,别处不动 只换西装颜色,别处一个像素没动。 ② 擦掉牛皮癣,底下干净 水印、促销贴一删,底下看着干净,促销贴盖住的一小块墨镜镜框也补全了。 ③ 一张图,多个版本 换色、去促销贴、左右换位,做了 7 个版本,没让 AI 重画一次。 小窍门,值得收藏: 要写明每层是什么,比如"第 1 层是水印"。 只说拆几层,所有字会挤在一层,删水印会连标题一起删。 局限:还不稳。同一张图拆 3 次,2 次把模特拆成了两层,图注也会放错层,得手动整理。 我的看法:要反复改主图、改活动图的女装电商运营和美工,值得试。 想自己试:下面链接里有免费在线试用页,传一张图,写清每层是什么就行,偶尔会卡。 开源地址: github.com/inclusionAI/Mi… 模型试用地址: openrouter.ai/inclusionai/mi… 你改主图最烦哪一步?评论区告诉我,我挑几个试。 🔗 View on Twitter 🔗 View Quoted Tweet

含视频地址
V

昨天还在说 Code Review 的实践,今天Anthropic就写了一篇文章详细描述它们 Code Review 的工程实践: claude.dev/blog/solving-c… 非常受用,可以好好读一下,核心观点是:代码多到人读不过来之后,人已经不 review 代码了,而是追求花最少的时间 并且回滚和事故又不增加 一个改动要过七层检查,几点也很有趣: 1 让 Agent 提 PR 之前先自证 证明做完了 测试 截图 等等 2 每个 PR 都有 AI review diff,对照整个仓库和 PR 的意图来审 多个 agent 同时找 bug 再由另一组投票,多数认定是真问题才发出来 纯风格类的意见直接丢掉 这个和我的 review-forge 的思路非常类似 3 按风险决定要几个人批 低风险不用人批准自动合并,普通功能一人批 最高风险的路径要两个人(我怀疑这步骤真的那么有用吗?人能看过来吗) 4 merge queue / feature flag / 灰度发布 先给内部员工用, 快速发现 快速回 feature flag 不用部署就能关掉 里面还有一个非常实用的思路 正好解答昨天多 agent review 的问题: review 要能收敛,agent 写 agent 审,有可能可以互相折腾个没完,文中说有个 PR 一夜之间来回改了五十多轮 git blame 一看,59% 被反复标记的都是第一轮时就已经存在的老代码 所以他们加了几条规则:最多三轮,超过就让作者退一步重新想方案 几轮之后只审新增的 diff 已经提过的意见不再重复。

G

DeepSeek-V4.1-Flash-1017 是不是 DeepSeek-V4.2-Flash !

A

Akshay Kothari @akothari I've been personal agent-maxing lately, and loving it. The new products are proactive, useful, and so fun. They get even better when they know me well. So I built a portable context vault in Notion and connected every agent to it. They write back new memories, skills, and preferences, then sync each morning. Now, whenever I try a new agent, the first thing I do is connect my vault, and it instantly gets all my preferences in one shot. I can also start a project with one agent, and switch over to another seamlessly. I shot a quick video to walk through the setup. LMK if you have any questions! 🔗 View on Twitter 🔗 View Quoted Tweet

含视频地址
J

please don't post spoilers on the movie 🙏🙏 at least until sunday lol

A

I've been using these virtual tabs in the @NotionHQ desktop app internally for the last two months, and it's made a huge difference in performance. No unnecessary reloads! 🔗 View on Twitter

含视频地址
G

哈哈哈,OpenCode 宣布 DeepSeek 4.1 Flash 免费,大家都免费了,神奇。

O

Real talk. PRs suck in the age of coding agents. There must be a better way. I agree with this post, agents are so capable now. Let them do the heavy lifting. They can generate (on demand) the right personalised views and artifacts that make things move a lot faster. Thorsten Ball @thorstenball Why are you still using pull requests? Is it for code review? If so, do you really think your or your colleagues catch bugs and mistakes that an Opus 5.5 or Fable or Astra won't find? You can literally spawn all three of them and have them check four times each. (Also, don't tell me you don't have a "stamp plz" Slack channel or group chat somewhere.) Is it for knowledge sharing? Surely there's better ways for that now than the PR, no? We have models that can generate explainer videos, presentations, podcasts, games, quizzes, walkthroughs, ... for any piece of code it can reach. Is CI the reason? Well ackshually, CI means continuous integration and its original meaning is the *opposite* of having long-lived branches and PRs. But, leaving that aside, your agents are hopefully already running the tests before they push something, and hopefully they can run as long as they want and don't block you so they can run the whole test suite and generate "irrefutable proof" and end-to-end demo videos and so on... And so they run the tests and confirm and then you push to a branch and everything runs again and then you merge and then it runs again? That doesn't make sense, does it? Maybe you work in open source and you accept contributions, in which case I can't speak to the value of pull requests. It's been 2 years since my last OSS contribution. But from what I heard, the time of the PR is coming to an end in OSS too? I honestly don't get why people still stick to PRs. With agents you can now move 10x faster, you can finally do real continuous integration, and get more confidence in the changes the agent made. Don't slow yourself down by having all the changes pile up in a PR. 🔗 View Quoted Tweet

O

안녕하세요 🇰🇷 Bags packed. Ollama is headed to Seoul ✈️ Korea is one of the most innovative AI markets in the world, and with such an active Ollama community in Seoul, we’ve been wanting to make this trip for a while. We’re really excited to finally go. This November, we will be in town meeting users, customers and partners, learning how we can further grow in the market. We’re also teaming up with @friendliai while we’re in Seoul. More on that to follow 👀

R

TypeScript is the new TypeScript 😂 When 𝚜𝚌𝚛𝚒𝚙𝚝𝚌-compiled, outperforms tsgo by 2-4x

S

当 Claude 写了 Claude Code 约 90% 的代码后,团队如何重新设计代码评审 ? Anthropic 没有取消代码评审,是把 “人读代码” 这个动作大部分交给了机器,把稀缺的人类注意力只花在真正需要判断力的地方。核心转变是:从“这段代码有人看过吗”变成“这个变更可能出什么问题,哪种检查(自动或人工)最适合抓住它”。 claude.dev/blog/solving-c… # 为什么必须改? 背景数字:2026 年 6 月到 9 月,合并的 PR 数量翻倍以上,而 revert 率下降超 40%。传统的“同事互相读 diff”模式在这个吞吐量下会先崩溃;人要么变成瓶颈,要么敷衍放行。 团队对成本的认识很清醒:人力时间 = 评审时间 + 修复坏代码的时间,压缩一头只会把成本转移到另一头。所以他们不追踪“评审覆盖率”这种虚荣指标,而转去追踪 “每个 PR 平均几个人类审批” 和 “等人审批的等待时间”,并以 revert 率 / 事故率作为护栏指标;目标是最多一个人在环(有时只有作者本人),且事故不比以前多。 # 七层防线:一个变更的一生 1. PR 之前的自我验证 — Claude 必须出示证据(测试输出、构建、截图)而不是声称完成;再用一个全新上下文的第二个 agent 审 diff。Boris Cherny(Claude Code 创造者)认为给 Claude 一个验证方法是“最重要的事”,效果提升 2–3 倍。反复出现的问题会被固化到源头:写进 CLAUDE.md(项目约定)和 REVIEW.md(给代码主人看的指引——失败长什么样、nit 上限、哪些路径跳过,且每条发现必须附文件/行号证据)。 2. 每个 PR 必过 AI 评审 — 内部 PR 上“实质性评审意见”占比从 16% 升到 54%;千行以上的大 PR 几乎总能查出问题。多个 agent 并行找 bug,再有 verifier agent 对每条发现投票才发出。发现分为 Important / Nit / Pre-existing,每条必须解决或说明理由。 3. 阻塞性的安全评审 — 独立的自动化通道,有未处理发现就不能合并。 4. 阻塞性的自动检查 — lint、类型、跨平台测试、构建;PR 模板强制填写“如何测试的”和“如何回滚”,且需一人签字。 5. 基于风险的人工审批 — 分类器定级:低风险(文档、文案)不需人工;中风险(普通产品变更,及缓存、自动更新器、系统提示词等敏感区)一人;高风险两人。关键规则:agent 的批准永远不能算人工批准;批准只覆盖一个 commit,有新提交就要重新审批。 6. 合并队列 + 特性开关 + 灰度 — 针对合并后 main 重跑检查;新行为先给 Anthropic 内部员工,再走 latest channel,最后进 stable。 7. 快速检测与回滚 — 开关无需重新部署即可关闭;事故复盘必问“哪一层本该拦住它”。 # 两个最有参考价值的工程细节 1. 评审器本身也是被持续评测的系统。 过去引发事故的 PR(经专家确认)构成一个 eval 集,评审器每天跑分,只有分数提升的改动才被保留;噪声则通过“人对评论的反应”和“在已知干净的 PR 上跑评审器”来度量。这本质上是把“评审质量”从主观感受变成了可优化的目标函数。 2. 收敛问题的解法。 曾有一个 agent 写的 CLI PR 一夜跑了 50+ 轮评审,而 git blame 显示约 59% 被标记的代码在第一轮之前就存在;评审 agent 在翻旧账而不是审新变更。修复手段:三轮封顶(超过就退回来重新考虑方案)、后续轮次只看增量 diff、标记 bug 类别而非单行、禁止重复发现。效果:一轮通过率 65%→78%,5 轮以上 PR 从 8.9% 降到 1.5%,平均评审轮次 2.08→1.32。这是 AI 评审 AI 代码时特有的“死循环”问题,他们的解法值得所有引入 AI reviewer 的团队抄作业。 # 人类还留在哪里? · 该不该做:方向、品味、范围; · 高危代码:计费、自动更新器、CI 工作流; · 可被复制模仿的架构决策; · 读证据:测试输出、截图、发现列表; · 为结果负责:每个上线变更背后必须有一个承担问责的人。 ClaudeDevs @ClaudeDevs Claude writes about 90% of Claude Code's code. From June to September, merged PRs more than doubled while the share reverted fell by more than 40%. We wrote about how we changed code review to get there, and how to adopt it: claude.dev/blog/solving-c… 🔗 View Quoted Tweet

F

十三亿美元,收购 Bumble。 10 月 13 日,约会软件 Bumble 以约 13 亿美元全现金卖给伊萨卡(Ithaca)——红杉合伙人古普塔和 Meta 前首席营收官赫格曼的新公司。它上市第一天值约 140 亿美元。 买家押的是:AI 越多,真人越值钱。可付费用户从 430 万掉到 316 万,AI 救得了约会吗?6 分钟讲透 👇 数据:Bumble 公告、SEC 文件、当事人推特、路透社。视频含 AI 合成配音与画面。 🔗 View on Twitter

含视频地址