Feed Entities Podcasts Deep Dives Developers About

[KongchangAI]

Real-time AI knowledge base. Every claim is traceable to its source, with data freshness under 24 hours.

Powered by 240+ first-hand AI sources

Knowledge

Feed
Hot Entities
Podcasts

Developers

CLI
MCP Server
REST API
About

© 2026 KongchangAI. The freshest, most accurate AI knowledge

Unverified75% confidenceFactTime unknown

OpenAI通过RLHF（基于人类反馈的强化学习）和专项安全微调使模型能够识别自杀意念、自我伤害等高风险内容模式

1

Sources

75%

Confidence

Long-term

Relevance

6/1/2026

First Seen

Sources

ChatGPT可信联系人功能详解：AI危机干预如何保护用户心理健康

twitterOpenAINewsroom

Related Entities

OpenAIcompany RLHFconcept

Related Claims

UnverifiedRLHF中非专业标注者更青睐流畅平和的摘要，可能训练模型系统性忽视小概率高风险信息71% similar UnverifiedOpenAI的InstructGPT论文证明，经过RLHF训练的1.3B参数模型在人类评估中优于未经对齐的175B模型69% similar Unverified现代大模型对齐训练高度依赖高质量偏好数据对，以 OpenAI 的 RLHF 和 RLAIF 为代表68% similar UnverifiedOpenAI在ChatGPT的RLHF训练过程中大量使用了'指令遵循'作为奖励信号，使模型倾向于逐条执行用户要求67% similar UnverifiedOpenAI、Anthropic等公司都已公开承认RLHF训练中存在谄媚倾向的副作用66% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/18433

API

curl https://kongchang.com/api/v1/knowledge/claims/18433

MCP

get_claim(id=18433)