aavisangle

I ask the question to agent from separate session without history to know more about my code

I use claude with remotion and ffmpeg to create final video.

Most of these apps work great in labs but fail in real life because everyone has their own different needs and the app should adapt to that. And rules, values and goals change day by day, so agents should adapt to those changes as well.

I think they must be using the Fable or maybe more capable model for internal use purposes.

You could use some smaller models, like parakeet, to figure out the users.

Yes it is and now it's a daily driver for me.

I liked the idea and I'm impressed, but here's what I'm thinking—what if the voice transcription gets it wrong? Like, voice can pick up similar-sounding words and transcribe them differently, you know?

Parakeet TDT 0.6B v3 (int8 CoreML, about 470 MB) runs on-device through FluidAudio's AsrManager, pinned to CPU plus the Neural Engine.

I think it works great on Mac but lags on Windows. The accuracy on Windows is lower than Mac.

How about digital twin of eon.io :)

what different features it offer than sqlight?

I got annoyed most by the keychain password and developing a Mac app without the developer ID, which is also a problem I have faced.

How do you do that? What's the architecture? Can you guide on that?

No, AI could have been trained on those codes but even after that AI can generate the code on its own as well.