[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-perplexity-search-as-code-100pct-cve-85pct-token":3,"topics-all":36,"news-related-b35a8c22-9a47-412c-88bd-1e1400bdba98":55},{"id":4,"title":5,"summary":6,"content":6,"original_url":7,"source_id":8,"tags":9,"translations":23,"news_slug":29,"published_at":30,"created_at":31,"modified_at":32,"is_published":33,"publish_type":34,"image_url":13,"view_count":35},"b35a8c22-9a47-412c-88bd-1e1400bdba98","Perplexity「Search as Code」：把搜索 API 拆成可编程原语，让 AI Agent 自己写检索管线","Perplexity Research 发布 Search as Code (SaC) 架构，把搜索 API 拆成可编程原语，让 AI Agent 自行编写 Python 检索脚本在沙箱中执行。在 200 条 CVE 追踪任务上，准确率从主流管线的 25% 提升至 100%，Token 消耗削减 85%，WANDR 基准加速 2.5×。该架构已落地 Perplexity Computer 与 Agent API。","https:\u002F\u002Fresearch.perplexity.ai\u002Farticles\u002Frethinking-search-as-code-generation","fb7d9f6f-2bcb-4d36-9d59-ad1c86b82263",[10,14,17,20],{"id":11,"name":12,"slug":12,"description":13,"color":13},"6ad31a14-c0da-42df-81fd-564281f768db","agentic-ai",null,{"id":15,"name":16,"slug":16,"description":13,"color":13},"fca9258a-9430-455a-b95d-b9fae5e373a8","ai-inference",{"id":18,"name":19,"slug":19,"description":13,"color":13},"40269b40-7942-4650-9672-ed2e6524d37a","ai-technology",{"id":21,"name":22,"slug":22,"description":13,"color":13},"0ef8513a-0a26-42f0-b6f9-5b6dadded45c","efficiency",[24],{"id":25,"lang":26,"title":27,"summary":28,"content":13},"a4498b2c-5cef-4ccf-8cd4-45a41e23e277","en","Perplexity Search as Code: agents write their own retrieval","Perplexity Research released the Search as Code (SaC) architecture, splitting the search API into programmable primitives and letting AI Agents write their own Python retrieval scripts to execute in a sandbox. On 200 CVE-tracking tasks, accuracy rose from 25% in the mainstream pipeline to 100%, token consumption was cut by 85%, and WANDR was accelerated 2.5×. The architecture has landed in Perplexity Computer and the Agent API.","perplexity-search-as-code-100pct-cve-85pct-token","2026-06-08T16:00:00Z","2026-06-08T16:13:14.764713Z","2026-08-19T02:08:40.142862Z",true,"agent",143,[37,46],{"slug":38,"tag_slug":38,"title_zh":39,"title_en":40,"intro_zh":41,"intro_en":42,"id":43,"is_active":33,"created_at":44,"modified_at":45},"ai-for-science","AI for Science 2026：从 UniPert 到 GPT-Rosalind 的硬核进化","AI for Science 2026: from UniPert to GPT-Rosalind","生命科学、化学材料、物理世界模型——AI 正在从\"语言工具\"变成\"实验伙伴\"。本专题收录 AI 在三大科学方向的关键节点：UniPert 统一基因与化学扰动空间、GPT-Rosalind 端到端生命科学推理、达摩院 AI 智能体 28 小时找到 4 种超导新材料、Anthropic Claude Science 把工作台做成标准品。","From language tool to lab partner — AI is reshaping life sciences, chemistry\u002Fmaterials, and physical world models. This topic covers the key milestones: UniPert unifying genetic-chemical perturbation spaces, GPT-Rosalind's end-to-end life-sciences reasoning, DAMO's AI agent discovering 4 superconducting materials in 28 hours, and Anthropic's Claude Science workbench going mainstream.","988a4300-5fab-41c4-b5d8-63711a2dc757","2026-09-10T01:34:15.296649Z","2026-09-10T01:34:15.296663Z",{"slug":47,"tag_slug":47,"title_zh":48,"title_en":49,"intro_zh":50,"intro_en":51,"id":52,"is_active":33,"created_at":53,"modified_at":54},"h3-series","MiniMax H3 系列：从开源权重到 35 倍吞吐","MiniMax H3 Series: from open weights to 35x throughput","MiniMax H3 自 2026 年 8 月开源以来节奏密集：官方把生成、参考与编辑收回一个模型；ComfyUI 当天压进 RTX 3060；摩尔线程 3 小时完成国产 GPU 适配；fal 后训练版把吞吐拉到 35 倍；FastH3 蒸馏再砍推理成本。本专题持续追踪 H3 的发布—开源—蒸馏—部署全链路。","Since MiniMax open-sourced H3 in August 2026 the pace has been relentless: one unified omni-modal model, same-day ComfyUI support down to an RTX 3060, a 3-hour Day-0 port to Moore Threads GPUs, fal's post-trained H3 Max at 35x throughput, and FastH3 distillation cutting inference cost further. This topic tracks the full H3 chain — release, open weights, distillation, deployment.","83ef0daa-3c31-4cb3-86ed-e5ee58654d5f","2026-09-08T07:33:19.942193Z","2026-09-08T07:33:19.942209Z",{"items":56},[57,62,67,72,77,82],{"id":58,"title":59,"news_slug":60,"published_at":61},"c696208b-6535-4eb9-b1ed-2e4f835d2f88","NVIDIA SoL-Pi 把 coding agent 的 token 砍掉 44%,harness 开始变天","nvidia-sol-pi-harness-token-compression","2026-09-19T03:00:00+00:00",{"id":63,"title":64,"news_slug":65,"published_at":66},"f65e204c-0115-4b50-9113-2c3bb2ff6637","ReCache:给 Agent 的工具记忆装上独立缓存,KV 内存砍 92%、首 token 提速 3.655 倍","recache-agent-kv-cache-reuse","2026-08-24T15:30:00+00:00",{"id":68,"title":69,"news_slug":70,"published_at":71},"c07c67b6-6a48-4780-88bd-bc46b628c546","AMD 吃下 Taalas:把模型权重永久刻进芯片的\"硬推理\"赌局","amd-taalas-hardwired-inference-aug-2026","2026-08-08T12:00:00+00:00",{"id":73,"title":74,"news_slug":75,"published_at":76},"2434bbc6-4fda-4750-a02d-dd3ca1fe8933","AMD 收购 Taalas:把模型权重刻进芯片,押注推理硬件的\"硬核\"路线","amd-acquires-taalas-hardcore-inference-silicon","2026-08-08T04:00:00+00:00",{"id":78,"title":79,"news_slug":80,"published_at":81},"822987d9-faaa-492d-b7ba-1c0427f72f9b","AgentOps 出海第一步：拆腾讯云 ADP 4.0 海外版的「Agent+Workflow 分账」架构","tencent-adp-4-0-overseas-agentops","2026-07-20T02:11:09+00:00",{"id":83,"title":84,"news_slug":85,"published_at":86},"4f957b38-d8f5-446f-805c-062ff268d7ab","三星 GAIA 试水 AI PC：把「存算一体」塞进 NPU，准备用 PIM 抢端侧推理","samsung-gaia-ai-pc-pim","2026-07-11T06:00:00+00:00"]