llimllib

my tests are against the Apple Intelligence model, fwiw, not any earlier model

interesting! I only tested against Parakeet v2 because my agent suggested it would be faster for English transcription (v3 is multilingual but somewhat slower, it suggested)

On my bench, parakeet-tdt-0.6b-v2 is 2x slower

I wonder if you're using different Apple models when you go through that app? I don't know

apple's is 5x faster than `large-v3-turbo` with whisper.cpp and in my test had somewhat worse performance, so it's a tradeoff

re: npm, if you upgrade your global node version, you will lose that installation, right?

Your agent writes secret.txt with the placeholder, and the tokenizing proxy replaces it with the token, then the agent reads secret.txt

Poorly! Apple’s facilities for this are the ones I know best, and they are woefully insufficient

right, but say you give the agent access to github and it can push as you, or make a gist; now it can easily exfiltrate your secret.

And that's just an easy case - really if it has any network access at all it can come up with a clever way to route a request through the network such that the key comes back somewhere in the request. If you scan for it inbound too, the machine can obfuscate it.

Our agents are trained to be so intensely helpful and they have such intricate knowledge of how things work that they will do some incredibly clever tricks to do what you ask them to do.

Operating systems ought to be providing us the utilities we need to safely sandbox processes (agent or otherwise), but they appear to not be interested in the job

This is what I currently do, but my software uses docker and docker mounts act as a bypass for the file system restrictions, plus docker processes started outside the sandbox allow network proxy escape.

Currently, I don't allow the agent access to docker, start docker myself, and then do short-lived sandbox-free sessions when the agent needs to do things that interact directly with docker; but that's annoying.

“Smoking gun”