@lifesinger: Heard from friends at LLM companies that analyzing user prompts across major domestic models reveals the top three usage scenarios: 1. Stock trading. Not only chatbots, but also agents like WorkBuddy—stock trading is the biggest use case. 2. Fortune-telling. Including Eastern mysticism like Bazi and love divination, as well as Western mysticism like MBTI and tarot...
Summary
Rumor has it that the top three scenarios for Chinese LLM user prompts are stock trading, fortune-telling, and 'others', with fortune-telling covering both Eastern and Western mysticism.
View Cached Full Text
Cached at: 07/16/26, 02:02 AM
I heard from a friend working at a large model company that after analyzing user prompts across major domestic models, the top three most-used scenarios are:
- Stock trading. Not just in chatbots, but also in agents like WorkBuddy — stock trading is the biggest use case.
- Fortune-telling. This includes Eastern esoteric arts like Ba Zi (Eight Characters) destiny analysis and marriage matching, as well as Western esotericism like MBTI and Tarot.
- Other. Stock trading is about money, fortune-telling is about fate. Beyond money and fate, everything else is indeed “other.”
Note: I don’t have the actual data — this is just hearsay. I hope some omnipotent Twitter friends can obtain the data to prove me right or prove me wrong.
Similar Articles
@FinanceYF5: How do regular users use AI in their personal lives? The latest analysis based on approximately 40,000 Claude conversations shows that health and wellness is the largest category, followed by career and professional development. The third category (relationships) shows a significant drop compared to the top two.
An analysis of approximately 40,000 Claude conversations reveals that the primary ways regular users employ AI in their personal lives are for health and wellness, followed by career development, with health-related queries making up the largest proportion.
@seclink: Fun fact: Currently, the specific implementation directions for multimodal large model startups typically include the following. If none of these interest you, don't follow the trend and go back to learning AI coding: 1. Game AI NPC / Agent middleware (e.g., end-cloud collaborative OmniNPC, empowering 3D character interaction and emotional storytelling...)
Summarizes several main implementation directions for current multimodal large model startups, including game AI NPC, enterprise-level multimodal Agent, content generation, embodied intelligence, and visual code assistants.
@ai_suxiaole: https://x.com/ai_suxiaole/status/2075425615264505958
WorkBuddy users shared 43 AI prompt scenarios, covering office work, creation, automation, data analysis, etc., helping users directly copy and use to improve productivity.
@kfk_ai: Poor Man's Agent Setup - Main model: deepseek-v4-flash (1M context), use SenseTime's free quota, register multiple keys, then bundle them with 9router to avoid rate limiting. Vision model: Qwen3-VL-30B-A3B-Thinking, SiliconFlow…
A user shares a configuration plan for building an Agent using a combination of multiple free or low-cost AI models, including modules for main model, vision, image generation, video, and voice.
@RookieRicardoR: Domestic models break through again, matching top models like Claude 4.6 and Gemini 3.1 Pro. Just tested Qwen3.7-Max, sharing some real thoughts. Last night I topped up as soon as the API went live and chose three tasks (see video) to test Qwen3.7-Max's frontend capabilities…
The user tested Qwen3.7-Max and believes it matches top models like Claude 4.6 and Gemini 3.1 Pro in frontend, computing power, and Agent capabilities. Its reasoning ability has significantly improved, and with monthly iteration speed, it has become a first-tier domestic model.