# StealthGPT 发布 Super 新一代 AI 人性化改写模型

- 来源：🚨 AI News | TestingCatalog (@testingcatalog)
- 发布时间：2026-09-09 04:44
- AIHOT 分数：32
- AIHOT 链接：https://aihot.news/items/cmtt5k6ui01q3rocpkdxmqhjc
- 原文链接：https://x.com/testingcatalog/status/2097425742959349988

## AI 摘要

StealthGPT 发布全新 AI 人性化改写模型 Super，从底层重构以针对最新一代 AI 检测器。Super 通过重写 AI 生成文本的结构、节奏和措辞，同时保留原意与可读性。StealthGPT 称，Super 能持续绕过 Pangram 检测，且不出现常见的人性化改写质量下降问题。

## 正文

StealthGPT has released Super, its newest AI humanizer, rebuilt from the ground up to target the latest generation of AI detectors.

Super works by rewriting the structure, rhythm, and phrasing of AI-generated or AI-assisted text while preserving the original meaning and readability.

StealthGPT reports that the new model can consistently get past Pangram without the usual quality drop associated with humanizers.

### 引用推文

> StealthGPT：We just killed Pangram, the world's most accurate AI detector. Today we’re announcing Super, a next generation humanization model. Our model makes content so un...