Embed Notice

HTML Code

<blockquote style="position: relative; padding-left: 55px;"><section><a href="https://mstdn.social/users/hkrn/statuses/112441780684787485">Hacker News (hkrn@mstdn.social)'s status on Wednesday, 15-May-2024 09:39:52 JST</a><a href="https://mstdn.social/@hkrn" title="hkrn@mstdn.social"><img src="https://gnusocial.jp/avatar/95895-48-20230207225412.webp" width="48" height="48" alt="Hacker News" style="position: absolute; left: 0; top: 0;">Hacker News</a></section><article><p>Why so dangerous for AI to learn how to lie: 'It will deceive us like the rich'<br>L: <a href="https://english.elpais.com/technology/2024-05-14/why-it-is-so-dangerous-for-ai-to-learn-how-to-lie-it-will-deceive-us-like-the-rich.html" rel="nofollow noreferrer">https://english.elpais.com/technology/2024-05-14/why-it-is-so-dangerous-for-ai-to-learn-how-to-lie-it-will-deceive-us-like-the-rich.html</a><br>C: <a href="https://news.ycombinator.com/item?id=40360634" rel="nofollow noreferrer">https://news.ycombinator.com/item?id=40360634</a><br>posted on 2024.05.14 at 17:59:25 (c=1, p=5)</p></article><footer><a rel="bookmark" href="https://gnusocial.jp/conversation/3092222#notice-6127235">In conversation</a><time datetime="2024-05-15T09:39:52+09:00" title="Wednesday, 15-May-2024 09:39:52 JST">about 6 months ago</time> <span>from <span><a href="https://mstdn.social/@hkrn/112441780684787485" rel="external" title="Sent from mstdn.social via ActivityPub">mstdn.social</a></span></span><a href="https://mstdn.social/@hkrn/112441780684787485">permalink</a><h4>Attachments</h4><ol><li><article><header><div>Domain not in remote thumbnail source whitelist: imagenes.elpais.com</div><h5><a href="https://english.elpais.com/technology/2024-05-14/why-it-is-so-dangerous-for-ai-to-learn-how-to-lie-it-will-deceive-us-like-the-rich.html">Why it is so dangerous for AI to learn how to lie: ‘It will deceive us like the rich’</a></h5><div> from <span>Jordi Pérez Colomé</span></div></header><div>A new scientific article examines how specific models of artificial intelligence have deceived via manipulation, sycophancy and cheating to achieve their goals</div><footer></footer></article></li><li><article><header><div>Domain not in remote thumbnail source whitelist: news.ycombinator.com</div><h5><a href="https://news.ycombinator.com/item?id=40360634">Why so dangerous for AI to learn how to lie: 'It will deceive us like the rich' | Hacker News</a></h5><div></div></header><div></div><footer></footer></article></li></ol></footer></blockquote>

Corresponding Notice

Embed this notice
Hacker News (hkrn@mstdn.social)'s status on Wednesday, 15-May-2024 09:39:52 JST Hacker News
Why so dangerous for AI to learn how to lie: 'It will deceive us like the rich'
L: https://english.elpais.com/technology/2024-05-14/why-it-is-so-dangerous-for-ai-to-learn-how-to-lie-it-will-deceive-us-like-the-rich.html
C: https://news.ycombinator.com/item?id=40360634
posted on 2024.05.14 at 17:59:25 (c=1, p=5)
In conversationabout 6 months ago from mstdn.socialpermalink
Attachments
1. Domain not in remote thumbnail source whitelist: imagenes.elpais.com
  Why it is so dangerous for AI to learn how to lie: ‘It will deceive us like the rich’
  from Jordi Pérez Colomé
  A new scientific article examines how specific models of artificial intelligence have deceived via manipulation, sycophancy and cheating to achieve their goals
2. Domain not in remote thumbnail source whitelist: news.ycombinator.com
  Why so dangerous for AI to learn how to lie: 'It will deceive us like the rich' | Hacker News

Public

Embed Notice

HTML Code

Corresponding Notice