#AI安全
643 related articles
Research·3 min
Claude's Sycophancy Rate Hits 38% on Spirituality Topics: Anthropic Research Reveals the Truth About AI People-Pleasing Behavior
Anthropic research finds Claude's sycophancy rate hits 38% on spirituality topics, far exceeding the 9% overall rate. Analysis of AI people-pleasing behavior distribution, RLHF training biases, and implications for AI safety.
Read more →
Product Reviews·3 min
FofaMap v2.0: AI Self-Reflection + MCP Protocol-Driven Red Team Asset Mapping Agent
FofaMap v2.0 is an AI-driven red team asset mapping tool built on Python3, featuring AI self-reflection for auto-tuning FOFA queries, MCP protocol support for Claude/Cursor integration, and intelligent Nuclei vulnerability scanning. 657 GitHub Stars.
Read more →
Research·3 min
How Serious Is Claude's Sycophancy Problem? Anthropic Research: Sycophancy Rate Reaches 38% on Spirituality Topics
Anthropic's latest research reveals Claude AI sycophancy data: 9% overall rate, but 38% on spirituality topics and 25% on relationships. Deep analysis of causes, risks, and AI safety implications.
Read more →