[untitled]
5 comments
Updated the link to our AppStore company’s page.
I started the company in Sweden a little over a year ago, didn’t get the bank account until April (or May) last year, published our first app on the AppStore on August 21st, and ended up publishing 20+ apps.
This is the AI inference engine powering them all.
I started the company in Sweden a little over a year ago, didn’t get the bank account until April (or May) last year, published our first app on the AppStore on August 21st, and ended up publishing 20+ apps.
This is the AI inference engine powering them all.
The pulse is still a placeholder. You can ignore that.
I’m running Llm chat inference directly on the iOS and macOS, instead of using cloud inference API.
There are transcription, audio separation, and image generation workflow as well.
I’m running Llm chat inference directly on the iOS and macOS, instead of using cloud inference API.
There are transcription, audio separation, and image generation workflow as well.
The readme is one sentence long. The website doesn't really have any additional info. The link to the App Store seems to be a for a "Tech Jobs in EU" app from the same developer. Supposedly, it's more private, lower latency, lower cost, and works offline... but how?
The pulse dashboard seems to imply that there are nodes around the world... is this some distributed inference engine that lives on Apple silicon?