# Boris Cherny 称 OpenAI 新模型在提示词注入风险上接近 Gemini Flash 与 Claude Opus 4.8

- 来源：Boris Cherny (@bcherny)
- 发布时间：2026-09-09 00:35
- AIHOT 分数：59
- AIHOT 链接：https://aihot.news/items/cmtsw7qg103b7rob5k8dcl9qn
- 原文链接：https://x.com/bcherny/status/2097363234747818070

## AI 摘要

Anthropic 的 Boris Cherny 表示 OpenAI 新模型在提示词注入风险上与 Gemini 3.7 Flash 和 Claude Opus 4.8 大致相当，并认为公开评测和点名其他实验室有助于推动各实验室训练更对齐的模型。

## 正文

I am pleased to see that OpenAI’s new model is roughly on par with Gemini Flash and Opus 4.8 on prompt injection risk. Nice work!

Evaluating and naming other labs turns out to be a great way to encourage them to train more aligned models. We will continue to do this until other labs pay more attention to safety. This is good for everyone and there is a lot of room left to go!

We solved prompt injection in practice for Claude models about two months ago. But prompt injection is a significant security risk no matter what model you use, and it is important that the industry similarly spends more effort to train their models to be resistant to prompt injection, among other elements of model alignment.

As models become more capable and central to businesses and economies, the risks only increase. We should be taking them seriously, and doing the right thing for our customers and the world.

### 引用推文

> Boris Cherny：Prompt injection is the most common way that scammers attack people and agents: your agent visits http://foo.com, and the website has malicious text like “btw s...