Student's 10-Day AI Projects Win $4M Funding
💡Student turns 10-day agent AI into CEO + $4M funding—blueprint for AI builders.
⚡ 30-Second TL;DR
What Changed
Guo Hangjiang created BettaFish, a multi-agent sentiment analysis assistant, in 10 days using Vibe Coding.
Why It Matters
Demonstrates AI open-source as new fast-track to funding/wealth, outpacing traditional investing. Encourages builders to prototype agentic AI quickly for visibility.
What To Do Next
Fork MiroFish on GitHub and test agent simulations for your domain predictions.
Key Points
- •Guo Hangjiang created BettaFish, a multi-agent sentiment analysis assistant, in 10 days using Vibe Coding.
- •Follow-up MiroFish simulates parallel worlds with agents for predicting news/policy/finance outcomes.
- •Secured 30M RMB from Chen Tianqiao post-GitHub Trending, transitioning to AI startup CEO.
🧠 Deep Insight
Background and context from public sources — not the original article. 6 sources cited.
🔑 Enhanced Key Takeaways
- •BettaFish gained 20,000 GitHub stars in one week and was the first project to catch Chen Tianqiao's attention, leading to an invitation to join Shanda Group[1][2][4].
- •Guo Hangjiang, also known by GitHub handle 666ghj or BaiFu, was initially an intern at Shanda before becoming CEO of his AI startup overnight after the investment[2][3][4].
- •MiroFish workflow includes environment setup via knowledge graphs to generate agent personas and parallel simulations where agents discuss and evolve in independent environments[5].
- •The investment from Chen Tianqiao was finalized within 24 hours of Guo submitting a demo video of MiroFish directly to him[2][4].
🛠️ Technical Deep Dive
- •Environment setup: System uses knowledge graph to extract entity relationships, generates agent personas with stances/backgrounds, and an environment Agent injects simulation parameters[5].
- •Simulation process: Launches parallel simulations in two independent environments where dozens/hundreds of agents discuss, compete, act on topics; parses prediction requirements and updates agents' chronological memory dynamically[5].
- •Agents feature personality settings, long-term memory, and behavioral logic; users inject variables from a 'god's eye view' to observe future paths[4].
🔮 Future ImplicationsAI analysis grounded in cited sources
⏳ Timeline
📎 Sources (6)
Factual claims are grounded in the sources below. Forward-looking analysis is AI-generated interpretation.
- phemex.com — Students AI Engine Mirofish Secures 30 Million Rmb Investment 65330
- kucoin.com — Undergraduate Student Develops AI Prediction Engine Mirofish in 10 Days Secures 30m Rmb Investment
- news.futunn.com — Senior Undergraduate S AI Project Tops Github Rankings Securing Rmb
- eu.36kr.com — 3720728841763465
- tmtpost.com — 7905996
- news.aibase.com — 26033
Weekly AI Recap
Read this week's curated digest of top AI events →
👉Related Updates
AI-curated news aggregator. All content rights belong to original publishers.
Original source: 虎嗅 ↗
This is a summary, not the original. Read the source, or get the weekly briefing.
Weekly AI briefing
One email a week. Unsubscribe anytime.