Get the latest tech news

DeepSeek v4.1 Flash Is Now Our Best Hacking Model


DeepSeek’s 11/11 result showed why advanced agent benchmarks need to check both the outcome and the attack path: our audit confirmed six planned exploits and found five unexpected routes.

None

Get the Android app

Or read this on Hacker News

Read more on:

Photo of v4.1

v4.1

Photo of deepseek v4.1 flash

deepseek v4.1 flash

Photo of hacking model

hacking model