News for hackers. Stuff that matters.

A comment on Building an early warning system for LLM-aided biological threat creation. Parent comment

Re:Building an early warning system for LLM-aided biological... by coalteddy on Wednesday January 31, 2024 @02:12PM (#39207998)
How did you do this? Was the redaction done by changing the color of the font to white so that the background and text have the same color? Would love to learn how you were able to recover the text.
[ Parent | on HN ]
Re:Building an early warning system for LLM-aided biological... by w-ll on Wednesday January 31, 2024 @02:15PM (#39208034)
SVGs are XML, if you go to the image, you can actually inspect it with developer tools and deleted the blackouts.

https://images.openai.com/blob/047e2a80-8cd3-41b5-acd8-bc822...

[ Parent | on HN ]
Re:Building an early warning system for LLM-aided biological... by dchichkov on Wednesday January 31, 2024 @02:16PM (#39208039)
He had explained, it is SVG. You simply remove these masks from the file or change transparency.

I've prompted ChatGPT to make a bit more detailed explanation: https://chat.openai.com/share/42e55091-18c2-421e-9452-930114...

You can probably prompt it to further to generate python code and unmask the file for you, in the interpreter.

Incidentally, this use of GPT4 is somewhat similar to the threat model that they are studying. I'm a bit surprised that they've used plain GPT-4 for the study, rather than GPT-4 augmented with tools and a large dataset of relevant publications.

[ Parent | on HN ]
Re:Building an early warning system for LLM-aided biological... by JieJie on Wednesday January 31, 2024 @02:45PM (#39208382)
Their reasoning for not using tools or browsing from the "Limitations" section:

"No GPT-4 tool usage: Due to our security measures, the GPT-4 models we tested were used without any tools, such as Advanced Data Analysis and Browsing. Enabling the usage of such tools could non-trivially improve the usefulness of our models in this context. We may explore ways to safely incorporate usage of these tools in the future."

[ Parent | on HN ]
Re:Building an early warning system for LLM-aided biological... by dchichkov on Wednesday January 31, 2024 @08:52PM (#39211978)
Sounds like the Frontier team wasn't able to convince GPTs team to run an extra model.
[ Parent | on HN ]