[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"blog-list":3},[4,19],{"_path":5,"title":6,"description":7,"slug":8,"date":9,"author":10,"category":11,"tags":12,"cover":18},"\u002Fblog\u002Fml-vs-llm-signal-generators","ML vs LLM as Signal Generators: Eight Dimensions Where the Choice Is Already Made","ML vs LLM as a trading signal generator, broken down across eight dimensions: cost shape, failure mode, reproducibility, interpretability, and the one row where the LLM actually wins.","ml-vs-llm-signal-generators","2026-05-25","StratCraft","insights",[13,14,15,16,17],"ai","trading","llm","machine-learning","signals","\u002Fblog\u002Fml-vs-llm-signal-generators.svg",{"_path":20,"title":21,"description":22,"slug":23,"date":24,"author":10,"category":11,"tags":25,"cover":27},"\u002Fblog\u002Fllm-trading-strategies-clone-problem","I Asked an LLM to Generate 20 Trading Strategies. 14 Were the Same Thing.","After generating 20 LLM trading strategies, 14 reused the same mean-reversion shape. Here is what breaks when AI skips the validation stack.","llm-trading-strategies-clone-problem","2026-05-15",[13,14,15,26],"backtesting","\u002Fbanner.png"]