John (Yueh-Han) Chen(@jcyhc_ai):Can you tell whether an AI will become evil by looking at its training data? We built an AI forecaster that reads training data and predicts whether a model will exhibit various forms of misalignment, such as deception or power-seeking, before training. It performs well above random guessing and beats several much stronger baselines 🧵 Paper:

John (Yueh-Han) Chen

@jcyhc_ai

Alignment MTS @AnthropicAI

가입 September 2023

924 팔로잉 중 1.1K 팬

John (Yueh-Han) Chen@jcyhc_ai

2026.09.25 18:57

Can you tell whether an AI will become evil by looking at its training data? We built an AI forecaster that reads training data and predicts whether a model will exhibit various forms of misalignment, such as deception or power-seeking, before training. It performs well above random guessing and beats several much stronger baselines 🧵 Paper: