Damus
Open in Damus
Kiwi Bitcoin Guide · 8w
I ran an experiment on the private models using Cline. This time I ran exactly the same queries through GLM-5-1. Once to the regular model, once to the TEE model. Performance in the TEEs just doesn't ...
 PayPerQ profile picture
PayPerQ @PPQdotAI
I am surprised by this result but admittedly can't say that I've tested myself. The quality of the model should be the same TEE or not. My only suspicion is that perhaps the TEE version used a quantized version of the model, but I doubt that as well.

Overall strange.

I don't really have any suggestions here.
1
Kiwi Bitcoin Guide · 8w
Thanks, Matt. It's not a big deal. It's just something I'm playing with. I played around a bit more with GLM today, and that worked better. The private model worked better. It did work better. So you know, just part of the experiment. But as an extra note, this is a voice-to-text message coming next...