Goodfire：用 30 倍更少的 rollout 预测 LLM 罕见失败
Predicting Rare LLM Failures with 30× Fewer Rollouts - Goodfire
AI 导读
Goodfire Research 提出一种方法，可用 30 倍更少的 rollout 预测 LLM 的罕见失败。其 Silico 定位为可解释性智能体，支持解释、调试并精确控制模型行为，适用于各类 AI 模型。
正文
当前显示原文，中文全文译文尚未就绪。
Better biosecurity monitors for AI agents via protein embeddings
Models know when they’re reward hacking — and we can catch them at scale
Silico is your interpretability agent.
Explain, debug, and precisely control model behavior with state-of-the-art interpretability methods and infrastructure
Silico works across all types of AI models