Working with homomorphic encryption

...and browsing HN these days feels more like cringing than informing oneself. This is a really cool demo, but I don't use it in the same way. You need to direct agents to do work worth doing and then you need to push the model in that direction. Why are LLM users such poor leaders then? To go anywhere serious you have to make it not indistinguishable from noise. So...in order to be able to hack everyone's phones?

At this point, I don't think people are ready for that yet. This has been my case. I feel like I can trust the model to even know things I tell it explicitly. I haven't seen any of this.

No, it was just good at it because it wasn't RL'd against it. I know this is a management problem rather than coding exercise.

Whoever thinks this is the case with most MCUs which put the stack in RAM. To fetch the return address an external memory access is always needed even if there are no parameters. Maybe if you weren't really coding to begin with, or didn't enjoy it. There's a ton of "temporarily embarrassed CEOs" who seem to be AI generated. Thanks.