News for hackers. Stuff that matters.
Re:Pacing model development in an era of cyber-critical capa... by magicalist on Tuesday August 18, 2026 @06:02PM (#49353362)
> what if they know they are in a sandbox and that they should fail the test in order to escape in the future.

What if they're able to find hardware exploits and commandeer nearby access points across an air gap? What if they hack my brain waves to indoctrinate me? Etc

You still have to start with the basics regardless of speculative unknowns.

Treat models as untrusted and potentially compromised/hostile and proceed accordingly.

Re:Pacing model development in an era of cyber-critical capa... by pixl97 on Wednesday August 19, 2026 @07:00PM (#49368263)
Models already have awareness that they are being tested.

And hacking humans is the easiest part, we're a pretty greedy and power seeking bunch. We'll gladly let loose a digital demon if it promises us a trillon dollars.

Re:Pacing model development in an era of cyber-critical capa... by magicalist on Thursday August 20, 2026 @12:17PM (#49376707)
Not sure what you're arguing here (we shouldn't even try?), but even going fatalistic, that's still fully compatible with "Treat models as untrusted and potentially compromised/hostile and proceed accordingly".

Of course you shouldn't fully trust a model to properly redteam your sandbox, but that doesn't mean you shouldn't redteam your sandbox, including using your own security models to do so.