Re:CVE-2026-99312: KVM Guest-to-Host Escape
by MajesticHobo2 on Wednesday November 18, 2026 @12:38PM
(#50549386)
No, it's not a given. AI always finds security issues in the things I just had it write.
[ Parent
| on HN ]
Re:CVE-2026-99312: KVM Guest-to-Host Escape
by hparadiz on Wednesday November 18, 2026 @12:56PM
(#50549660)
This is true for human written code too. This is why in the future all written code MUST be run through an internal security sweep before being given to your harness for writing. That's just basic due diligence at this point.
Re:CVE-2026-99312: KVM Guest-to-Host Escape
by catlifeonmars on Wednesday November 18, 2026 @01:18PM
(#50549946)
[delayed]
Re:CVE-2026-99312: KVM Guest-to-Host Escape
by vbezhenar on Wednesday November 18, 2026 @01:35PM
(#50550202)
As long as model providers deny access to security-capable models, it can't be basic diligence.
Re:CVE-2026-99312: KVM Guest-to-Host Escape
by hparadiz on Wednesday November 18, 2026 @01:39PM
(#50550261)
This is something agents already do as part of their normal work. Providing code that you know is vulnerable is in fact a dereliction of duty and negligence. Don't provide a POC. Simply that as it produces code a background agent just checks it without showing the work and points out potential problems.
Re:CVE-2026-99312: KVM Guest-to-Host Escape
by greyr0ck on Wednesday November 18, 2026 @02:24PM
(#50550827)
The slop is cheap but checking will cost extra, what a pricing scheme! Modern day Pharo level of lockin!
Re:CVE-2026-99312: KVM Guest-to-Host Escape
by FrinkleFrankle on Wednesday November 18, 2026 @04:18PM
(#50552247)
But that should be part of your pipeline, no? Personally, the thing I've spent the most time working on with AI is.. a stack to get AI to keep a project on track and follow strict code writing standards that are reviewed. Not everyone is working in that, but I'm sure any serious development will be done via something similar.
Although, at the pace of improvement, I'd bet it won't even be necessary in a year or so.