build1 publisher
One risk word in the reasoning trace cut a live SOPHUSDT order to 0.8 times size
The F-072 rule engine scans an LLM's chain of thought for risk words and multiplies position size by 0.8 when it finds one. On the trade its author logged, both constants it applied were already in the model's own reasoning.
Publishers:dev.to
Reality
- Evidence34
- Adoption8
- Hype gap+45
- Incentives80
- Confidence45