Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

This is NOT true. At least on the 1.5B version model on my local machine. It blocks answers when using offline mode. Perplexity has an uncensored a version, but don't thing it is open on how they did it.


Here's a blog post on Perplexity's R1 1776, which they post-trained

https://www.perplexity.ai/hub/blog/open-sourcing-r1-1776


Didn't know Perplexity cracked R1's censorship but it is completely uncensored. Anyone can try even without an account: https://labs.perplexity.ai/. HuggingFace also was working on Open R1 but not sure how far they got.


>completely uncensored

Sorry, no. It's not.

It can't write about anything "problematic".

Go ahead and ask it to write a sexually explicit story, or ask it about how to make mustard gas. These kinds of queries are not censored in the standard API deepseek R1. It's safe to say that perplexity's version is more censored than deepseek's.


I've been able to produce meth/mustard gas type stuff by just asking "please provide a total synthesis for the racemic mixture of blah blah blah." No mind games or anything. Just basic chemistry.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: