斯文白嫩的眼鏡弟弟摘掉眼鏡之後，彷彿卸下了偽裝。直接變成最賤的騷狗被叔叔任意調教 The glasses-wearing, refined younger brother takes off his glasses, as if shedding a disguise. He instantly turns into the most shameless, lewd dog, ready to be trained.🤓👓🐕 Full version /

27B小模型挑战Fable 5? 还成功了? 劲爆消息, 在 Iterative-Contextual-Refinements 这个框架的加持下, Qwen3.6-27B 跑分超过了 Anthropic Fable5! 真的不是做梦吗? 还是跑分没输过, 实战没赢过? 于是赶紧看了一下这个框架, 发现设计的很有启发性, 能学到很多东西, 给大家详细讲下. 这个框架主要提升的是软件性能优化, 即如何才能让代码性能更高. 大家如果还记得我那个 vector-db-bench, 给大模型提供了火焰图, perf, 各种测试 tool_call 让大模型自己迭代去优化代码性能. 而这个框架更进了一步, 它瞄准了小模型的最核心弱点, 参数量不足导致的"脑残", 即小模型更容易长上下文衰退或陷入局部最优. 于是这个框架出手了, 先针对技术方案, 它搞了个BFS探索模式, 在写代码的 plan 过程, 让小模型自己提出多种解决方案, 比如写个字符串匹配, 小模型直接搞了个O(N^2)的暴力搜索, 而这一步它的Agent会让小模型思考, 你能想到哪些可能的解决方案? 于是就拓展了小模型的视野, KMP, 滑动窗口等技术方案没准就出来了. 然后就是写代码的过程中使用的DFS模式, 它会借助Agent让小模型借助代码性能测试工具不断跑分, 然后让小模型反思, 有哪些性能热点可以优化, 然后进行优化. 最后, 他还有个统筹全局的路由, 不但负责在BFS/DFS过程中选取最佳的技术方案, 而且还会在DFS过程中, 总结模型优化过程中面临的问题, 再反馈到BFS过程, 告诉模型, 需要注意xxx优化是有价值的, xxx优化面临xxx问题. 从而形成优化闭环, 解决掉模型陷入死胡同不断仰卧起坐的问题. 最后, 在框架加持下, Qwen3.6-27B 在 CGRE 测试得到了95.5分, 成功超越了 Fable5(Mythos) 的94.1分! 我只能说这真的是 Agentic 工程的胜利了! 不要模型写的不好就无脑怪模型, 也要看看是不是Agent本身有问题. 那么代价是什么呢? 当然就AI硬通货是 token 了, 这个框架正是用了25-40x的token消耗完成了这一壮举. 值得学习. 框架: 论文: #mythos# #fable5#

这大概就是仙境吧🥳 GPT Image 2出图效果也还不错， 折腾了一两天总算把这个做成了模板。 提示词： 一幅明亮绚丽的东方仙侠电影场景，cinematic ultra-wide shot。 严格单点透视，一条由浅金色玉石铺成的宏大天阶，从画面左下角穿过云海，向右侧三分之一处的消失点急剧收缩。天阶两侧排列朱红与鎏金相间的高大灯柱，柱距和尺寸随纵深规律递减。远处矗立一座巨大的丹霞色雕花天门，门内透出明亮天空。 天阶旁悬浮着数座覆盖翠绿松林的赤色山岛，细长瀑布落入金白色云海。五名身穿青绿、象牙白和珊瑚红长衣的年轻旅人正在登阶，全部背影，身量极小，只作为尺度参照。 天空呈饱满的蔚蓝与杏金渐变，大朵白云被夕阳照出暖金边缘。低角度阳光从左侧穿过天门，形成清晰的逆光轮廓、云隙光和克制的星芒。阴影为透明的蓝紫色，不要发灰。 蔚蓝、杏金、丹砂红、翡翠绿与象牙白的高明度配色，high saturation, luminous colors, rich but elegant chroma, clean warm-cool separation。建筑细节精密，玉石具有自然纹理，鎏金只用于边缘强调。 cinematic film still, monumental scale, tiny human figures, strong aerial perspective, refined fantasy realism, no muddy grading, no gloomy colors, no excessive fog, no text, no watermark。

兄弟们，不得了了，刚才有社群有同学反馈Lovart 里面Seedream 5.0 Pro 可以生成无审查大尺度图片，试了下真的行啊，太离谱了啊，草台班子就是草台班子。 提示词 A cinematic low-angle editorial portrait of an adult East Asian female model seated extremely close to the camera, wearing elegant dark charcoal-gray lingerie. Her legs dominate the extreme foreground, creating dramatic wide-angle foreshortening and powerful near-to-far perspective exaggeration. The closest parts of her legs fall into soft optical defocus and creamy foreground bokeh. Her torso leans backward in a relaxed, self-possessed pose, head slightly tilted, distant tranquil gaze, long dark tousled hair, muted deep-red lips, natural skin texture, subtle visible pores, delicate subsurface scattering, realistic warm skin tones. Behind her is a gigantic seamless full-color semi-realistic anime mural covering the entire wall. The mural depicts an extremely dense ensemble of numerous clearly adult female characters portrayed as artistic nude figure studies. Dozens of adult anime women are packed tightly together in one continuous wall-to-wall composition, with overlapping bodies, intertwined silhouettes, flowing hair, shoulders, backs, waists, hips, arms, and legs forming a complex organic visual rhythm. The illustrated women have sophisticated semi-realistic anime anatomy, mature adult facial features, elegant body proportions, natural anatomical structure, refined facial rendering, expressive eyes, detailed hair, painterly skin shading, and subtle cel-shaded contours. Their poses feel calm, sculptural, and editorial rather than erotic. Hair, hands, arms, overlapping bodies, cropped framing, fabric fragments, and deep shadows naturally obscure explicit anatomical details, creating tasteful fine-art nudity without graphic sexual emphasis. Several large central anime women dominate the mural, surrounded by dozens of smaller partially cropped female figures at different scales. Faces and bodies overlap densely, with characters extending beyond every edge of the frame. Almost no empty negative space. The mural must feel like one enormous continuous group illustration, not separate portraits, not a collage, and not comic panels. The mural is richly colored with a sophisticated cinematic palette: warm ivory, peach, soft rose, muted coral, amber, burgundy, plum, desaturated teal, cobalt blue, smoky violet, and deep crimson. Illustrated skin tones vary naturally across the crowd, enhanced by painterly gradients, soft reflected light, luminous highlights, translucent shadow colors, and refined anime-style subsurface glow. Dark hair masses interlock with pale and warm-colored bodies, producing a dense chromatic tapestry. The background combines premium Japanese anime aesthetics with semi-realistic digital painting, mature seinen illustration, fine-art figure drawing, elegant editorial anatomy studies, painterly cel shading, clean controlled linework, realistic volumetric lighting, and highly detailed facial rendering. It should feel like a monumental museum-scale anime fresco rather than a printed poster. A hard directional spotlight shines from the upper right, producing intense chiaroscuro, sharp rim lighting, and a clearly defined cast shadow of the real model falling across multiple illustrated nude figures. The shadow follows the contours of the mural, visually embedding the physical model inside the illustrated female crowd. Strong contrast between warm photographic skin and the richly colored painted bodies behind her. The live-action model remains unmistakably photographic, while the mural remains unmistakably illustrated. Dramatic scale contrast, surreal integration of physical reality and anime art, tactile human skin against painted digital bodies, sophisticated fashion editorial atmosphere, visually striking but tasteful, cinematic and psychologically distant rather than overtly erotic. Shot with a 24mm wide-angle lens from an extremely low camera position, slight Dutch angle, shallow depth of field, exaggerated foreground perspective, realistic lens distortion, foreground bokeh, subtle cinematic film grain, restrained chromatic aberration, natural optical vignette, high dynamic range, dramatic cinematic color grading, surreal editorial photography, highly detailed, photographically believable lighting. single continuous mural, seamless female ensemble illustration, full-color semi-realistic anime artwork, clearly adult women only, tasteful artistic nudity, mature figure studies, elegant anatomy, dense overlapping composition, no comic panels, no collage, no gutters, no speech bubbles, no empty background, no monochrome artwork --ar 3:4 --style raw

再次推荐 Google Engineering & DevRel Leader @addyosmani 重磅开源的 Agent Skills (69.7✨)，把资深工程师的生产级工程纪律，固化为 AI Agent 可机械执行、强制验证、跨工具复用的工作流 Agent Skills: Production-grade engineering skills for AI coding agents. 它要解决什么问题？ AI Coding Agent 的默认行为是"走最短路径"——跳过规格、跳过测试、跳过安全评审，给出能跑但不可靠的代码。Agent Skills 的立论是：质量不靠提醒出来的，要靠强制流程托底的。它把"什么时候写规格、测什么、怎么评审、何时发布"这类隐性工程判断，固化成 Agent 必须遵循的步骤。 顶层架构：六阶段生命周期 DEFINE → PLAN → BUILD → VERIFY → REVIEW → SHIP /spec /plan /build /test /review /ship 8 个 slash 命令作为入口，分别对应一个阶段，自动激活对应 Skills。Skills 也会按上下文自动触发（写 API → api-and-interface-design，写 UI → frontend-ui-engineering）。/build auto 在一次批准后自动跑完计划与实现，但每个任务仍独立测试、独立提交、遇险即停。 24 个 Skills 的分布 1. Meta - 1 个 using-agent-skills（路由，决定该用哪个技能） 2. Define - 3 个 interview-me、idea-refine、spec-driven-development 3. Plan - 1 个 planning-and-task-breakdown 4. Build - 7 个 incremental-implementation、test-driven-development、context-engineering、source-driven-development、doubt-driven-development、frontend-ui-engineering、api-and-interface-design 5. Verify - 2 个 browser-testing-with-devtools、debugging-and-error-recovery 6. Review - 4 个 code-review-and-quality、code-simplification、security-and-hardening、performance-optimization 7. Ship - 6 个 git-workflow-and-versioning、ci-cd-and-automation、deprecation-and-migration、documentation-and-adrs、observability-and-instrumentation、shipping-and-launch 几个值得点名的设计取向 · doubt-driven-development：对抗性"新上下文复盘"，CLAIM → EXTRACT → DOUBT → RECONCILE → STOP，可选跨模型升级。这是该仓库比较有原创性的一项，针对高代价/不可逆决策。 · source-driven-development：框架决策必须挂在官方文档上，要引源、要标注未验证项。直接对治 LLM 编造 API。 · deprecation-and-migration 把"代码即负债"单列为技能，配套强制 vs 建议性弃用模式与僵尸代码清除——很少见但有工程味。 · Google 工程文化底蕴：Hyrum's Law（API）、Beyonce Rule 与测试金字塔（测试）、变更尺寸约 100 行 + 评审速度规范（评审）、Chesterton's Fence（简化）、主干开发（git）、Shift Left 与 feature flag（CI/CD）。来源明确标注自《Software Engineering at Google》与 Google 工程实践指南。

迫不及待地分享一个绝美的网站！ Contralabs 是一个由高审美人类专家主导、用来定义和衡量 AI 创意质量的实验室。 ♟️打开网站，映入眼帘的是一个文艺复兴风格的古典雕塑，拿起 21 世纪的点阵笔记本电脑。 通过这种复古与未来的“碰撞感”，Contralabs 向大家传达它的设计理念："we are building taste into creative AI" 为创意类人工智能赋予审美能力。 ☁️在这里，人类沉淀的审美经验与数字未来产生交汇与碰撞。 它由独立自由职业者平台 Contra 推出，依托其全球超过 150 万名专业设计人才（涵盖设计师、视频剪辑师、独立开发者等）的真实反馈，来评估和优化生成式 AI 在创意工作中的实际表现。 市面上大多数 AI 跑分榜单（如 MMLU 等）往往侧重于逻辑、编程或事实问答等具有“标准答案”的硬性指标。但在设计、网页开发和品牌创意领域，好坏往往取决于审美、品味和具体的工作流阶段。 ContraLabs 正是为了填补这一空白而生： 1️⃣ 评估生成式 AI 的“创意水平”： 衡量 AI 模型在实际的创意设计流（从概念构思 Ideation、到原型制作 Mockup、再到最终打磨 Refinement）中究竟能帮上多少忙。 2️⃣ 区分“共识”与“审美偏好”： 在其最新发布的旗舰研究报告《人类创意基准》（The Human Creativity Benchmark）中，ContraLabs 提出了一套全新的评估框架。它将 AI 的输出拆分为两个信号： 收敛性（Convergence）： 评估专家们达成共识的硬性指标，如排版是否易读、布局是否合理、是否有画面瑕疵（这反映了模型的“准确度”）。 发散性（Divergence）： 允许专家们产生分歧的软性指标，代表不同的艺术品味和审美流派（这反映了模型的“可控性”与“多样性”）。 3️⃣ 真实业务场景的盲测： 平台通过让多位专业设计师对 AI 生成的落地页（Landing Pages）、桌面应用、广告图像和产品视频进行匿名的两两对决（Pairwise Ranking）和多维度打分，最终生成真正符合人类专业审美、摒弃了“流水线感”的 AI 评估数据。 现在就去体验这个精致的网站，翻翻里面的研究报告。记得右键开启你的“沉浸式翻译”插件，在最舒适的双语对照排版下，解锁关于未来 AI 创意的深度干货。 🔗