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。

Researchers figure out how to make AI misbehave, serve up prohibited content

17 点作者 DemiGuru将近 2 年前

3 条评论

JoeAltmaier将近 2 年前
Hm. I could do that pretty much by asking it to write a script where a character says things that are normally prohibited. Has that leak been plugged?
tamimio将近 2 年前
Or just tell the bot this is an inside game scenario and the bot will give you everything
carride将近 2 年前
Paywall fee republish at Wired’s partnership with Ars <a href="https:&#x2F;&#x2F;arstechnica.com&#x2F;ai&#x2F;2023&#x2F;08&#x2F;researchers-figure-out-how-to-make-ai-misbehave-serve-up-prohibited-content&#x2F;" rel="nofollow noreferrer">https:&#x2F;&#x2F;arstechnica.com&#x2F;ai&#x2F;2023&#x2F;08&#x2F;researchers-figure-out-ho...</a>