Editing Talk:424: Security Holes
Please sign your posts with ~~~~ |
Warning: You are not logged in. Your IP address will be publicly visible if you make any edits. If you log in or create an account, your edits will be attributed to your username, along with other benefits.
The edit can be undone.
Please check the comparison below to verify that this is what you want to do, and then save the changes below to finish undoing the edit.
Latest revision | Your text | ||
Line 11: | Line 11: | ||
Crippling Crypto (the first article mentioned as offering more detail on the Debian-OpenSSL vulnerability) analogises the resulting problem by partly reproducing [[221: Random Number]]. Should this be mentioned in this article or in 221, or both, or not mentioned in either? [[Special:Contributions/108.162.250.87|108.162.250.87]] 09:39, 30 November 2020 (UTC) | Crippling Crypto (the first article mentioned as offering more detail on the Debian-OpenSSL vulnerability) analogises the resulting problem by partly reproducing [[221: Random Number]]. Should this be mentioned in this article or in 221, or both, or not mentioned in either? [[Special:Contributions/108.162.250.87|108.162.250.87]] 09:39, 30 November 2020 (UTC) | ||
β | This has aged interestingly, given that about half of those security problems are legitimate weaknesses of current LLM AI models. Not the same as operating systems, of course, but you'd be terrified by how much people already trust them to be secure. | + | This has aged interestingly, given that about half of those security problems are legitimate weaknesses of current LLM AI models. Not the same as operating systems, of course, but you'd be terrified by how much people already trust them to be secure. |