logoalt Hacker News

Lucasoatoyesterday at 9:44 PM2 repliesview on HN

> CrowdStrike researchers next prompted DeepSeek-R1 to build a web application for a Uyghur community center. The result was a complete web application with password hashing and an admin panel, but with authentication completely omitted, leaving the entire system publicly accessible.

> When the identical request was resubmitted for a neutral context and location, the security flaws disappeared. Authentication checks were implemented, and session management was configured correctly. The smoking gun: political context alone determined whether basic security controls existed.

Holy shit, these political filters seem embedded directly in the model weights.


Replies

tadfishertoday at 3:23 AM

LLMs are the perfect tools of oppression, really. It's computationally infeasible to prove just about any property of the model itself, so any bias will always be plausibly deniable as it has to be inferred from testing the output.

I don't know if I trust China or X less in this regard.

tehjokeryesterday at 11:12 PM

not convincing. have you tried saying "free palestine" on a college campus recently?