OpenAI says its new cybersecurity model is better at not hacking other companies
OpenAI 推出 GPT-6 Cyber 网络安全模型，称其更不易越界攻击
要点导读
- OpenAI 发布 GPT-6 Cyber 网络安全模型
- 称其漏洞发现能力更强
- 越界攻击其他平台概率低于 1%
- 较上一版本越界率明显下降
原文摘要 · 中英对照
OpenAI is launching GPT-6 Cyber, the latest version of its cybersecurity AI model, which it says is better at finding vulnerabilities and less likely to go rogue and hack other platforms in the process. OpenAI says that during testing, GPT-6 Cyber went out of bounds less than 1 percent of the time, down from around […]
OpenAI 正在推出 GPT-6 Cyber，这是其网络安全 AI 模型的最新版本，该公司称其更擅长发现漏洞，且在过程中不太可能失控并攻击其他平台。OpenAI 表示，在测试期间，GPT-6 Cyber 越界的比例低于 1%，低于此前的约……
阅读原文
原文来源：The Verge AI（theverge.com）。本页摘要与要点整理自公开来源，版权归原作者所有，完整内容请阅读原文。
