TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Consistent Jailbreaking Method in o1, o3, and 4o

8 点作者 rhavaei3 个月前

5 条评论

numbers3 个月前
I have a jailbreaking method that's 100% effective but I can't share it until the authors of this article share theirs because it seems like we can just make up claims about effectiveness without sharing any evidence.
评论 #42978515 未加载
viccis3 个月前
A new jailbreaking method with this level of effectiveness against these models that can produce the entirety of those unsafe outputs?<p>Yes.<p>May I see it?<p>No.
评论 #42978494 未加载
评论 #42978529 未加载
lunw3 个月前
Nice to see some cool jailbreaks being worked on. Hope people patch it soon so we can look at the methodology.
thatguy09003 个月前
A lot of handwringing in this article about the harm jailbreak cause and the responsibility to not release them, then the example of the harms that could be caused is racist jokes? And instructions on making a bomb, that by definition of being in the dataset can already be found on the internet, probably just with a Google search? Instructions to create fake social media accounts? It&#x27;s very silly to read this level of seriousness like these models would make criminal masterminds if they but released the jailbreak. Let&#x27;s be real, all the jailbreaks would be useful for in real life is creating custom erotica.
评论 #42978573 未加载
tacocat3613 个月前
If this is real, could be a cool read after it&#x27;s patched.
评论 #42978830 未加载