Why would I want non-deterministic behavior here though?

If I want to max uptime, I write a tool to track/monitor. Then write a small agent (non-ai) that monitors those outputs and performs your remediation actions (reset something, clear something, etc, depends on service).

Do I want Claude re-writing and breaking subscription flow because it detected an issue? No.

So the exploiters have deprecated that version of spyware and moved on I see. This has been the case every other time. The state actors realize that there's too many fingers in the pie (every other nation has caught on), the exploit is leaked and patched. Meanwhile, all actors have moved on to something even better.

Remember when Apple touted the security platform all-up and a short-time later we learned that an adversary could SMS you and pwn your phone without so much as a link to be clicked.

KSIMET: 2020, FORCEDENTRY: 2021, PWNYOURHOME, FINDMYPWN: 2022, BLASTPASS: 2023

Each time NSO had the next chain ready prior to patch.

I recall working at a lab a decade ago where we were touting full end-to-end exploit chain on the same day that the target product was announcing full end-to-end encryption -- that we could bypass with a click.

It's worth doing (Apple patching) but a reminder that you are never safe from a determined adversary.