AI Safety
Nature and Science Retract 150 AI-Generated Papers With Fabricated Data
Major scientific journals retract 150 papers found to contain AI-generated fabricated data and images. Publishers announce mandatory AI-assisted authorship disclosure and enhanced fraud detection screening.
2025年8月3日来源：Nature
相关资讯
Anthropic's Mechanistic Interpretability Research Finds 'Features' in Claude's Reasoning
5月1日 · Anthropic
Anthropic Achieves Breakthrough in Mechanistic Interpretability Research
4月28日 · Anthropic Research
Anthropic Publishes Updated Model Spec: New Guidelines for AI Behavior
5月15日 · Anthropic
AI Synthetic Media Detection in 2025 Elections: Global Challenges and Solutions
7月28日 · OECD AI Policy Observatory
OpenAI CEO Sam Altman's Congressional Testimony: AI Safety, Jobs, and the Path to AGI
5月7日 · OpenAI
China Implements Comprehensive Generative AI Regulations with New Requirements
5月9日 · Cyberspace Administration of China
延伸阅读 · 相关教程
AI in Government: How Cities and Federal Agencies Are Using AI to Serve Citizens Better
Case studies from Singapore, Estonia, and US federal agencies deploying AI in public services
LLM Security: Defending Against Jailbreaks and Prompt Injection Attacks
Constitutional prompts, output filtering, and layered defense strategies
AI Content Moderation at Scale: Building Trust and Safety Systems
Multi-modal content classification, human review workflows, and policy enforcement
AI Red Teaming: Systematic Techniques for Finding LLM Vulnerabilities
Jailbreaks, prompt injection, adversarial inputs, and building robust AI safety testing