On-Device AI: TTS, STT & Chat

UPDATE: The Developer's prompt response below took care of the problem after I unplugged my iPad from the charging brick, while running the app, my device no longer overheated. I really like this app and appreciate the rapid response support. Having access to LLMs offline (when wi-fi connectivity isn't available) is a much appreciated gift. Thanks🙏🏼 ............................. ORIGINAL REVIEW: How can I use this app on my ipad pro (12.9" m1 fifth gen 16mb device with 1TB memory) but without it overheating my device??? For example, I just ran a simple search and analysis of cutlery "super-steels" and my device screen promptly heated up to the touch. No other apps I have used elicit this speedy and high a temperature increase. I am concerned that continuing to use it will damage my iPad. Developer, please discuss and identify how to fix this problem. Please note that I downloaded only one of the two LLMs recommended by the app for this iPad's capabilities.

I honestly can’t fathom how this app is free. It’s like stumbling upon a treasure chest in a sea of paid apps that don’t even offer a fraction of these features. The fact that you can run AI models locally, with this much precision and functionality, is mind-blowing. Meanwhile, so many “premium” apps charge a hefty price for far less. Now, about the negative reviews—let’s address the elephant in the room. If your 6GB iPhone can’t handle an 8B model, that’s not the app’s fault; it’s basic tech knowledge. Calling the app a “scam” because of hardware limitations is akin to blaming a sports car for not fitting in a bicycle lane. Let’s be real: you wouldn’t try to cram a piano into a shoebox, so why attempt to run a high-performance model on a device not equipped for it? This app is a gem, and any criticism rooted in misunderstanding is just noise. It’s evident that the developers behind this masterpiece know their stuff, and the fact that it’s accessible to everyone at no cost deserves applause. If you’re into cutting-edge AI and have the right hardware, this app is a game-changer. Don’t sleep on it!

The ability to make a shortcut that allows for running an LLM in the background is great. Do you believe that there are any extra features you can add for shortcut compatibility? For example: - Defining a system prompt - Continuing a conversation - Defining a preset conversation (to be used as synthetic context) then generating a response to the defined conversation ... all in Shortcuts :D There are just a few problems, however. I've come to find that a message may just stop generating out of the blue, and that in Shortcuts, generated responses from the same query are always the same. Aside from these minor issues, thank you so much for implementing this feature, I can see many practical shortcut workflows coming up in the near future, and maybe you could even put together a community of Shortcut users where they show off cool little applets and masterpieces through the power of prompt engineering!