Enhances AI reasoning by implementing a two-stage deliberate attention mechanism to filter noise and ensure factual grounding.
The System 2 Attention skill provides a framework for deliberate, multi-pass reasoning within transformer-based workflows. It mitigates common AI issues like sycophancy and context-clutter by first extracting objective facts and removing irrelevant or leading information before generating a final response. This skill is particularly useful for complex problem-solving, factual verification tasks, and scenarios where the AI must remain objective despite biased input prompts or 'opinion-seeking' noise in the context.
主要功能
01Context regeneration for noise reduction
02Factual grounding validation and scoring
03Two-pass attention architecture (Fast vs. Deliberate)
04Sycophancy reduction through opinion filtering
05Compositional integration with GF(3) triads
062 GitHub stars
使用场景
01Reducing 'people-pleasing' bias in analytical tasks
02Verifying claims against large, unstructured documentation sets
03Enhancing technical troubleshooting by filtering irrelevant log data
