Consistent Jailbreaks in GPT-4, o1, and o3 - General Analysis

generalanalysis.com

Consistent Jailbreaks in GPT-4, o1, and o3 - General Analysis

generalanalysis.com

ooli2@lemm.ee to

Technology@beehaw.orgEnglish · 5 days ago

This report identifies vulnerabilities in GPT-4, o1, and o3 models that allow disallowed content generation, revealing weaknesses in current alignment mechanisms.

You must log in or register to comment.

Chat

Technology@beehaw.org

technology@beehaw.org

Create a post

You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: [email protected]

A nice place to discuss rumors, happenings, innovations, and challenges in the technology sphere. We also welcome discussions on the intersections of technology and society. If it’s technological news or discussion of technology, it probably belongs here.

Remember the overriding ethos on Beehaw: Be(e) Nice. Each user you encounter here is a person, and should be treated with kindness (even if they’re wrong, or use a Linux distro you don’t like). Personal attacks will not be tolerated.

Subcommunities on Beehaw:

This community’s icon was made by Aaron Schneider, under the CC-BY-NC-SA 4.0 license.

Visibility: Public

This community can be federated to other instances and be posted/commented in by their users.

22 users / day
22 users / week
22 users / month
22 users / 6 months
1 local subscriber
38K subscribers
50 Posts
0 Comments
Modlog