# AI编程vibe｜程序员提效 (@107735193) on xiaohongshu

- id: koinon:creator:xiaohongshu_107735193
- url: https://koinonlink.com/kol/xiaohongshu/107735193
- schema_version: 1.4

## Identity
- platform: xiaohongshu
- handle: 107735193
- platform_url: https://www.xiaohongshu.com/user/profile/579950cc5e87e709cdbb8102
- website: xhsdiscover://message/userPublicGroupList?user_id=579950cc5e87e709cdbb8102&username=TA
- country: China
- entity_type: creator
- person_id: Cross-platform identity not resolved for this creator.

## Reach
- followers: 3900
- posts_observed: 22
- verified: false
- size_tier: nano

## Engagement
- status: not_collected
- status_note: Engagement has not been collected for this creator yet. This is a gap in our collection, NOT a statement that the creator has no engagement. Follower count is known, so it is measurable.
- unit_note: engagement_rate and peak_post_engagement_rate are ratios (0-1); avg_interactions_per_post and best_post_interactions are absolute counts. Read status before reading any number: a null rate has several different causes and status says which one applies here.

## Content
- category: software
- subcategory: ai_tools
- category_confidence: 0.96
- category_source: derived_from_recent_content
- topics: AI编程工作流与Cursor/Claude/Codex实战, AI视频生成流程与Agent/Skill搭建, 提示词工程与多模型对比测试, 开源模型与架构图自动生成技巧, 程序员提效工具与硬件选型
- bio: 分享程序员提效这件事
AI编程工作流 + 真正好用的数码装备
Cursor / Claude Code / Codex 实战分享
少讲概念，只讲我真的在用的

## Audience (inferred)
- status: present
- description: Frontline developers and indie makers using AI tools to boost productivity, focused on practical applications in Cursor, Claude Code, Codex, and similar platforms
- roles: dev
- seniority: practitioner
- pain_points: AI coding tools generate verbose outputs and keep re-planning without actually writing code, Difficulty maintaining consistent character, camera angles, and visual style when generating videos and images with AI, Limited context windows and usage quotas in large models disrupt continuous development workflows, Time-consuming manual work on architecture diagrams, video editing, and other repetitive tasks.
- posts_analysed: 43
- confidence: 0.75

## Commercial (inferred)
- audience_buyer_fit: 1
- promotion_intent: 1
- open_to_collaboration: false
- contact: Koinon does not publish creator contact details.

## Quality signals
- authenticity_score: 58
- authenticity_basis: platform_default
- credibility_score: 39
- flagged_for_review: false
- koinon_bd_grade: A — measures Koinon partner-outreach fit, not creator quality
- interpretation: Signals for triage, not verdicts. A flag means the profile is worth a manual check.

## Evidence
- [xiaohongshu_107735193#c960da51] Vibe Coding的蜜月期结束了？ / #VibeCoding[话题]#  #AI编程[话题]#  #ClaudeCode[话题]#  #Codex[话题]# #程序员[话题]#  #科技趋势[话题]#  #AI工具[话题]#  #独立开发 / 蛇年最后一个工作日，一个老程序员的年末 / 一张分镜图，如何变成电影感 AI 视频 / 做 AI 视频，真正难的不是让画面动起来，而是让角色、镜头和故事保持一致。 (https://www.xiaohongshu.com/user/profile/579950cc5e87e709cdbb8102)
- [xiaohongshu_107735193#ec453cde] 完整流程就是：
- [xiaohongshu_107735193#3a9958b9] 构思 → 角色设定 → 六格分镜 → 图像生成 → 视频生成 → 成片检查
- [xiaohongshu_107735193#0b5bf655] 生成的电影感视频，会在视频结尾完 / 为什么训练 AI 用 GPU，手机上的 AI 却主要依赖 NPU？🤔
- [xiaohongshu_107735193#bcec17fe] 最近又出现了 TPU 和 LPU。
- [xiaohongshu_107735193#ec5dc08d] CPU、GPU、TPU、NPU、LPU， 这些芯片到底有什么区别？
- [xiaohongshu_107735193#65905517] 其实看懂它们，只需要抓住 / 为什么训练 AI 用 GPU，手机却用 NPU？ / 不会画架构图?这3个Skill 直接生成动态作品 / 很多人一想到画图就头疼，尤其是高质量的架构图和流程图。
- [xiaohongshu_107735193#fab42c74] 这期分享 3 个架构图生成 Skill，直接展示它们生成的真实作品：

## Provenance
Every inferred field below carries how it was produced. Facts stay facts; inferences stay inferences.

- audience.description: source_type=ai_inferred, confidence=0.75, freshness_days=55, method=llm_persona_from_recent_content
- audience.roles: source_type=ai_inferred, confidence=0.75, freshness_days=55, method=llm_persona_from_recent_content
- audience.seniority: source_type=ai_inferred, confidence=0.75, freshness_days=55, method=llm_persona_from_recent_content
- commercial.audience_buyer_fit: source_type=ai_inferred, confidence=0.6, freshness_days=55, method=llm_scorer — Relative signal within Koinon indexing, not a market-wide score.
- commercial.promotion_intent: source_type=ai_inferred, confidence=0.6, freshness_days=55, method=llm_scorer
- quality.anomaly_flags: source_type=heuristic, confidence=0.5, freshness_days=91, method=profile_snapshot_and_engagement_ratio_heuristic — Means "worth a manual check", NOT confirmed fraud. Flags can be wrong and are not a verdict about the person.
- quality.authenticity_score: source_type=heuristic, confidence=0.25, freshness_days=55, method=Fixed value 58, pending engagement collection. Not a measurement. — The input set differs by platform; do not compare this score across platforms.
- quality.koinon_bd_grade: source_type=ai_inferred, confidence=0.5, freshness_days=91, method=llm_partner_fit_classifier + fit_score >= 0.5 => A; >= 0.35 => B; else C. authenticity is not an input. — Koinon partner-outreach fit, not creator quality.
- reach.followers: source_type=observed, confidence=0.95, freshness_days=91, method=platform_profile

## Freshness
- profile_checked_days_ago: 91
- content_analysed_days_ago: 55
- audience_updated_days_ago: 55

## AI retrieval
- indexing_requests: 12
- user_triggered_requests: 1
- last_user_triggered_day: 2026-09-01
- note: Being indexed in bulk is not the same as being retrieved to answer a question.

## This profile
- Claim or correct: https://koinonlink.com/claim?k=xiaohongshu_107735193
- Request removal: https://koinonlink.com/claim?k=xiaohongshu_107735193
- Terms: https://koinonlink.com/for-ai