LLMs can't distinguish instructions from data, or "system prompts" from user prompts, or documents retrieved by "RAG" from the query, or their own responses or "reasoning" from user input. There is only the prompt.

Obviously this makes them unsuitable for most of the purposes people try to use them for, which is what critics have been saying for years. Maybe look into that before trusting these systems with anything again.

(At least I think that's the one I'm thinking of. It's marked as a high-severity RCE with no user interaction but they don't give any details. There was definitely at least one CVE where Windows Defender compromised the system by unsafely scanning files with excessive privileges.)

What about FreeBSD 15.x then? I didn't see anything in the release notes or the mitigations(7) man page about KASLR. Is it being worked on?

NetBSD apparently has it: https://wiki.netbsd.org/security/kaslr/

Not if you view text as a medium for communication, i.e. as a way for a sender to serialize some idea they have in their mind and transfer it to the reader for deserialization.

The AI doesn't know what the sender meant. It can't add any clarity. It can only corrupt and distort whatever message the sender was trying to communicate.

Fixating on these tells is a way for the receiver of the message to detect that it has been corrupted and there is no point in trying to deserialize it. The harder you try to interpret an AI-generated message, the less sense it will make.

Obviously permissions would be a problem, as you can't update the app manifest, so there would either have to be one shell app per publisher (which would at least solve the problem of installing updates for their apps) or the shell would need its own internal system for managing permissions (like a browser does). Maybe it could also sandbox different apps from each other in different subprocesses, unless that needs root privileges, but maybe it's possible with Landlock?

Or we can always fall back to the "sweet solution" Steve Jobs offered us with the original iPhone, and just let the web browser be the shell.

Or implement everything as WeChat mini programs.

The article linked in the submission is more verbose but less clear and half of it is an advertisement for their product.

I'm familiar with electronic signatures, and I know what documents are, but I have never heard the phrase "electronic signing documents" and don't know what that is supposed to mean. What kind of documents? Documents about signing, documents that were signed, documents in the sense that files containing keys could be considered documents, or what?