Skip to content

#DeepSeek

2 items today
Today10/6Tue
  1. Hacker News · MCP78

    Flash-Agents: an MCP plugin that hands Claude Code's coding tasks to a DeepSeek Flash worker

    Flash-Agents is a Claude Code plugin that delegates bounded coding work—implementing slices, porting tests, reviewing diffs, mapping out a codebase—to a DeepSeek V4.1 Flash worker, while Claude keeps architecture, acceptance criteria, and final review.

    Why it matters: The author outsources Claude Code's coding tasks to a DeepSeek Flash worker and shares the sandbox, patches, and measured data, so you can judge the cost and safety boundaries for yourself.

10/4Sun
  1. 佬刘AI78

    Planning with GPT, Execution with DeepSeek: A Cost-Saving Two-Model Workflow

    The author has GPT (gpt-6.1-sol, reasoning tier high) handle planning, key decisions, and acceptance in Codex, and calls DeepSeek-V4.1-Flash through the official DeepSeek Harness to write code, run experiments, and fix bugs—together producing a local PDF toolkit with five working features.

    Why it matters: The author splits the work between GPT for planning and DeepSeek for execution to get a PDF toolkit running, and shares three prompts plus cache usage data that can carry over to cutting costs on long tasks.

10/2Fri
  1. Hacker News · Vibe Coding 讨论22

    中国的 vibe-coding 之都良渚能告诉我们什么关于 AI 热潮的事

    杭州良渚聚集了一批逃离 9-9-6 的开发者,在这里以 vibe-coding 方式构建 AI 产品,如模拟飞行环境的专注计时器 FocusFlight、AI 工作流工具 YouMind,以及用大语言模型解读八字的 FateTell,后者已有数十万用户。北京已将 AI 列为国家优先事项并推出 A.I. Plus 计划,但良渚的软件更偏向小众趣味,类似手工作坊式产品。

    Awaiting translation

10/1Thu
9/30Wed
9/29Tue
9/9Wed
9/3Thu
  1. Cline · Blog74

    Cline 如何把 1100 万用户迁移到最大一次 harness 升级

    Cline 把 VS Code 扩展从约 76,000 行单体核心迁移到 Cline SDK,并自建灰度发布机制:一个安装包内打包 loader、legacy 和 next 两套扩展,由 PostHog 功能开关按百分比决定激活哪套,崩溃时自动回退到 legacy,开关可随时降到 0% 作为 kill switch。

    Awaiting translation

    Why it matters: Cline 官方复盘如何把 1100 万用户的 VS Code 扩展迁到新 harness,含灰度机制与前后指标对比。

8/29Sat
8/27Thu
  1. Cline · Blog71

    Cline 实测八个模型做 IMO 2026:DeepSeek V4 Flash 以 0.12 美元拿到金牌线

    Cline 让八个模型在自家 harness 里做 IMO 2026 六道题,证明由 GPT-5.5 和 Claude Opus 5 双盲按 0–7 分制评分、Gemini 3.1 Pro 仲裁,金牌线为 29 分。

    Awaiting translation

    Why it matters: Cline 用同一套 harness 盲评八个模型做 IMO 2026,给出分数与单次成本对照,可看开源权重模型的实际性价比。

8/17Mon
  1. V2EX · Vibe Coding22

    迫于 DeepSeek 涨价,求推荐替代接入 Claude Code 的模型/API

    有开发者因 DeepSeek v4 pro 涨价,在 V2EX 求推荐能替代接入 Claude Code 的模型/API。其需求包括支持超大上下文与最大 effort、同时兼容 Anthropic API 和 OpenAI API,并提到 ChatGPT 5.6 Sol 的 Ultra 模式也非 100% 成功率。评论区有人推荐 5.6luna,称速度稍慢但更便宜。

    Awaiting translation

8/14Fri
8/10Mon
8/6Thu
8/5Wed
  1. Chen Dahuang · AI Coding 实录66

    DeepSeek V4 Flash 正式版深度体验:便宜、快、1M 上下文、内置搜索

    作者深度体验几天 DeepSeek V4 Flash 0731 正式版后总结:便宜到跑批处理、Agent 循环和几十轮对话账单基本无感,速度快到配合 Agent 工具循环每步几秒内完成,1M 上下文可容纳整个仓库和完整对话历史、无需频繁 compact,结合 Cache 打折长上下文成本还能再降。

    Awaiting translation

8/4Tue
8/2Sun
6/15Mon
5/23Sat
5/6Wed
4/28Tue