Maybe this one can stop writing a fucking essay in code comments.
I'm now no longer surprised just how consistently all the gemini models overcomplicate coding challenges or just plain get them wrong.
Claude is just consistently spot on. A few salient comments for tricky code instead of incessantly telling me what it's changed and what I might want to do, incorrect assumptions when it has the code or is something we've discussed, changing large amounts of unrelated code (eg styles). I could go on.
Shame I'm too tight to pay for Claude RN though...
It was just obviously worse than using the anthropic website. That was the only explanation for why it was so bad. They could offer it free because it was stupid even if the same version (maybe less resources). Or maybe I was just unlucky but that's what it seemed to me.
I think the big limiting factor is having it learn what the infinite number of parameters in different synths, etc actually make it sound like, and then being able to make the model be able to produce music by using and configuring them instead of just spaffing out crap music.
If it could do that it'd give the tweakability it needs, but I think it would basically involve training a model for each instrument.
Yeah, there’s a few, and I probably should have included more plugins. I don’t mind the built in Ableton vocoder. The built in Logic Pro one is a bit average. I like the XILS 201 plugin, but it’s not as nice as many of the hardware vocoders I tested. I guess it depends what you‘re after and how much vocoder you need.
(Note that the XILS 201 plugin requires iLok. I think iLok sucks.)
Thanks! I’ll give it a listen. Number of bands doesn’t necessarily dictate the quality of results — the Electro-Harmonix V256 has 256 bands, and it’s not even in the top 5 out of the vocoders I tested, imo.
Definately, Vocodex is probably one of the few vocoders you can turn to if you want something specifically uncharacteristic of a classic vocoder sound.
I feel like that’s a theme for Arturia’s plugins. I have their 1176 compressor and some other stuff. They’re nice, but use tons of CPU and can be a bit flaky at times.
I'm now no longer surprised just how consistently all the gemini models overcomplicate coding challenges or just plain get them wrong.
Claude is just consistently spot on. A few salient comments for tricky code instead of incessantly telling me what it's changed and what I might want to do, incorrect assumptions when it has the code or is something we've discussed, changing large amounts of unrelated code (eg styles). I could go on.
Shame I'm too tight to pay for Claude RN though...
reply