Embed Notice

HTML Code

<blockquote style="position: relative; padding-left: 55px;"><section><a href="https://techhub.social/users/Techmeme/statuses/112305952896228090">Techmeme (techmeme@techhub.social)'s status on Sunday, 21-Apr-2024 08:21:01 JST</a><a href="https://techhub.social/@Techmeme" title="techmeme@techhub.social"><img src="https://gnusocial.jp/avatar/75284-48-20221217065620.webp" width="48" height="48" alt="Techmeme" style="position: absolute; left: 0; top: 0;">Techmeme</a></section><article><p>Researchers: when given 15 CVE descriptions, GPT-4 autonomously exploited 87% of the vulnerabilities, compared to 0% for every other model tested (Thomas Claburn/The Register)</p><p><a href="https://www.theregister.com/2024/04/17/gpt4_can_exploit_real_vulnerabilities/" rel="nofollow noreferrer">https://www.theregister.com/2024/04/17/gpt4_can_exploit_real_vulnerabilities/</a><br><a href="http://www.techmeme.com/240420/p11#a240420p11" rel="nofollow noreferrer">http://www.techmeme.com/240420/p11#a240420p11</a></p></article><footer><a rel="bookmark" href="https://gnusocial.jp/conversation/2968793#notice-5901191">In conversation</a><time datetime="2024-04-21T08:21:01+09:00" title="Sunday, 21-Apr-2024 08:21:01 JST">about 7 months ago</time> <span>from <span><a href="https://techhub.social/@Techmeme/112305952896228090" rel="external" title="Sent from techhub.social via ActivityPub">techhub.social</a></span></span><a href="https://techhub.social/@Techmeme/112305952896228090">permalink</a><h4>Attachments</h4><ol><li><article><header><div>Domain not in remote thumbnail source whitelist: regmedia.co.uk</div><h5><a href="https://www.theregister.com/2024/04/17/gpt4_can_exploit_real_vulnerabilities/">GPT-4 can exploit real vulnerabilities by reading advisories</a></h5><div></div></header><div>While some other LLMs appear to flat-out suck</div><footer></footer></article></li><li><article><header><div>Domain not in remote thumbnail source whitelist: regmedia.co.uk</div><h5><a href="https://www.techmeme.com/240420/p11">Researchers: when given 15 CVE descriptions, GPT-4 autonomously exploited 87% of the vulnerabilities, compared to 0% for every other model tested</a></h5><div></div></header><div>By Thomas Claburn / The Register. View the full context on Techmeme.</div><footer></footer></article></li></ol></footer></blockquote>

Corresponding Notice

Embed this notice
Techmeme (techmeme@techhub.social)'s status on Sunday, 21-Apr-2024 08:21:01 JST Techmeme
Researchers: when given 15 CVE descriptions, GPT-4 autonomously exploited 87% of the vulnerabilities, compared to 0% for every other model tested (Thomas Claburn/The Register)
https://www.theregister.com/2024/04/17/gpt4_can_exploit_real_vulnerabilities/
http://www.techmeme.com/240420/p11#a240420p11
In conversationabout 7 months ago from techhub.socialpermalink
Attachments
1. Domain not in remote thumbnail source whitelist: regmedia.co.uk
  GPT-4 can exploit real vulnerabilities by reading advisories
  While some other LLMs appear to flat-out suck
2. Domain not in remote thumbnail source whitelist: regmedia.co.uk
  Researchers: when given 15 CVE descriptions, GPT-4 autonomously exploited 87% of the vulnerabilities, compared to 0% for every other model tested
  By Thomas Claburn / The Register. View the full context on Techmeme.

Public

Embed Notice

HTML Code

Corresponding Notice