TGTGInsighttelegram intelligenceLIVE / telegram public index
← OnePlus OS Update Tracker

TGINSIGHT SIMILAR POSTS

查找相似内容

Source channel @OnePlusOTA · Post #607 · 5月27日

OnePlus Nord 2 OxygenOS 12.1 C.04 IND System • Fixed the issue that the lock screen interface displayed abnormally when charging • Fixed the issue that the screen brightness displayed abnormally in certain scenarios • Fixed the occasional issue that the desktop text displayed abnormally in certain scenarios Camera • Optimized the anti-shake effect when shooting videos • Optimized the speed of enabling Camera in certain scenarios Others • Fixed the issue of abnormal crash when enabling Fortnite MD5 Component (my_manifest): c949151afe63f1cfe9fda80d0d541abc Component (my_product): 408223966738c5d0a71f39b211bb1592 Component (my_bigball): 8253f6c910a4bc7cbfe044b3b1f79751 Component (my_stock): f08eb9a61ed03567965cbc76d980e6a3 Component (my_heytap): 28db2abbedc1eafc8947749e91b197fc Component (my_carrier): f0b3b8bd50cc13f4d2a1ebdad9f75f22 Component (system_vendor): e5d935f73c54cc08ae04c9e5abeefe20 Component (my_region): ceb333df4f651e82e5c71a9d76da3273 SHA-1 Full: a3de2e204668cc33c7134bf062bb5f6873a28bce Size Component (my_manifest): 1.22 MB (1278656) Component (my_product): 413.80 MB (433902450) Component (my_bigball): 578.54 MB (606645588) Component (my_stock): 615.30 MB (645192760) Component (my_heytap): 508.90 MB (533621509) Component (my_carrier): 1.04 MB (1088872) Component (system_vendor): 2.49 GB (2675632293) Component (my_region): 3.35 MB (3513520) Full: 4.56 GB (4893267850) Downloads ColorOS Global Server: Component (my_manifest) Component (my_product) Component (my_bigball) Component (my_stock) Component (my_heytap) Component (my_carrier) Component (system_vendor) Component (my_region) Google OTA Server: Full Exported by MlgmXyysd Color OTA Bot@OnePlusOTA #Oxygen#denniz#India#Component#Full#Stable#DN2101

Results

找到 1 条相似帖子

搜索 #agentskills

当前筛选 #agentskills清除筛选
AI一线|ShareCentre

@ShareCentre · Post #7129 · 2026/03/26 07:45

Google DeepMind 发布 Gemini API 开发者技能:用 Agent Skills 弥合模型知识鸿沟 Google DeepMind 于 3 月 25 日发文介绍其构建的 Gemini API 开发者技能(gemini-api-dev),旨在通过 Agent Skills 规范弥合大语言模型的知识鸿沟。测试显示,Gemini 3 系列模型在启用该技能后,代码生成正确率从不足 7% 大幅提升至接近 100%,但前提是模型需具备强大的推理能力。 ⚙️ 技能内容 该技能包含四部分: - API 高级功能集概览 - 当前模型和各语言 SDK 说明 - 各 SDK 基础示例代码 - 文档入口点列表(作为真实信息源) 技能已开源在 GitHub,支持通过 Vercel skills 和 Context7 两种方式安装: npx skills add google-gemini/gemini-skills --skill gemini-api-dev --global npx ctx7 skills install /google-gemini/gemini-skills gemini-api-dev 📊 评测结果 - 评测集:117 个 prompt,覆盖 Agent 编码、聊天机器人、文档处理、流式内容等场景 - 失败标准:生成的代码使用了旧版 SDK - Gemini 3.0 Pro/Flash:基线仅 6.8%,启用技能后大幅提升 - Gemini 3.1 Pro:基线 28%,启用技能后几乎全部通过 - Gemini 2.5 系列:也有提升,但远不如 3.x 系列——强推理能力是关键 - SDK Usage 类别通过率最低(95%),部分失败来自明确要求使用 Gemini 2.0 模型的 prompt 📎 相关链接 原文:https://developers.googleblog.com/closing-the-knowledge-gap-with-agent-skills/ GitHub:https://github.com/google-gemini/gemini-skills Agent Skills 规范:https://agentskills.io Google ADK Skills 文档:https://google.github.io/adk-docs/skills/ #Google#AI#AgentSkills#GeminiAPI#ADK#开发者工具