Strategy Hallucination
The model emits plausible trading logic that looks quantitative but has no market rationale, no statistical grounding, or invalid assumptions.
It creates code that passes syntax checks while smuggling in false causality.結構化洞察
交易軟體世代：從 MT4 到 LLM
四代交易軟體的結構化比較：指標時代平台、策略框架、系統管線，以及 LLM 提示詞轉程式碼工作流程。
四代交易軟體
關鍵轉變不僅在於語言或使用者體驗。每一代都改變了交易者用來表達、測試和實踐策略構想的核心抽象層。
| 面向 | Gen 1: Indicator Era~2005-2012 | Gen 2: Strategy Era~2012-2018 | Gen 3: System Era~2018-2023 | Gen 4: LLM Era2023-present |
|---|---|---|---|---|
| Time period | ~2005-2012 | ~2012-2018 | ~2018-2023 | 2023-present |
| Representative products | MT4 / MQL4 | Backtrader, freqtrade, vnpy | QuantConnect, WorldQuant BRAIN | ChatGPT + brokerage API |
| Core abstraction | Modular indicators | Packaged strategy logic: entry, exit, sizing | Feature engineering pipeline | Natural language to code |
| Typical workflow | Drag indicators, set conditions, backtest | Write strategy code, optimize parameters, backtest | Build feature pipeline, train, validate, execute | Prompt, generate strategy, backtest |
| Main progress | Indicators moved from books and forums into reusable components | Complete strategies became packageable, shareable, and reproducible | The pipeline became the product, with standardized validation | Generation is fast and the entry barrier is low |
| Typical trap | Indicator worship and holy-grail thinking | Parameter overfitting: genetic search finds coincidence, not robustness | Data leakage and survivorship bias | Strategy hallucination and backtest overfitting blindness |
| Failure root cause | Rules are manual and lack systematic validation | The optimization target is backtest return, not robustness | Model complexity hides data-quality problems | The model skips infrastructure accumulated across the first three generations |
LLM 時代的兩種失敗模式
LLM 降低了生產策略程式碼的成本，但並未消除對驗證基礎設施的需求。
Backtest Overfitting Blindness
The model treats a profitable backtest as validation and misses leakage, parameter mining, unstable regimes, or survivorship bias.
It accelerates curve fitting because generation speed multiplies untested variants.LLM 常見的 Z 分數模式生成
spread = asset_a.close - hedge_ratio * asset_b.close
z_score = (spread - spread.mean()) / spread.std()
if z_score > 2:
short(asset_a)
long(asset_b)
elif z_score < -2:
long(asset_a)
short(asset_b)模型 + 工具
模型不是交易系統
LLM 包裝在工具中才有用。嚴謹的交易技術棧包括資料驗證、定價引擎、執行邏輯、風控措施、監控和部署紀律。
Jane Street 風格的系統展現了這一模式：模型只是更大工具鏈中的一層，而非整個產品。
StratCraft 定位
為第二代與第三代開發者打造的基礎設施
StratCraft 並非宣稱自己是第五代。它為策略框架與系統管線的開發者提供本地端 C++ 等級的回測效能、外掛隔離以及可重複的驗證工作流程。