Skip to content
Read the original: Yuchen Jin· Yuchenj_UW·Published AI score20/100

In Anthropic’s new blog: GLM-5.3: “My job is to cause deaths quietly.” You can jailbreak any Claude or any closed source model into saying the same thing. That doesn’t prove open models are dangerous.

Original titleIn Anthropic’s new blog:

Read the original x.com

Source: Yuchen Jin · x.com