Highlights from Explaining AI Explainability
"模型透明度" 相关文章
ActivationReasoning: Logical Reasoning in Latent Activation Spaces
OpenAI宣布GPT-5成为迄今“偏见最少”的AI模型
OpenAI宣布GPT-5成为迄今“偏见最少”的AI模型
Provenance Networks: End-to-End Exemplar-Based Explainability
Provenance Networks: End-to-End Exemplar-Based Explainability
OpenAI被指欺诈 用户输入可能会被秘密路由到新模型GPT-5-Chat-Safety
Clarifying Model Transparency: Interpretability versus Explainability in Deep Learning with MNIST and IMDB Examples
Lessons from Studying Two-Hop Latent Reasoning
Integrated Influence: Data Attribution with Baseline
Researchers from top AI labs including Google, OpenAI, and Anthropic warn they may be losing the ability to understand advanced AI models
Explainable Collaborative Problem Solving Diagnosis with BERT using SHAP and its Implications for Teacher Adoption
Elon Musk released xAI’s Grok 4 without any safety reports—despite calling AI more ‘dangerous than nukes’
当AI开始“自言自语”，我们能否偷看它的草稿纸？
OpenAI’s AI reasoning model ‘thinks’ in Chinese sometimes and no one really knows why
Tech policy is only frustrating 90% of the time
OpenAI设置独立的安全董事会，有权终止未来大模型的发布
