Qwen 3.8 27B scores 52 on UPI transactions

We (wife and I) de-googled ourselves about a year ago. I hope this trend continues. By the way, just want to drop a model into their existing toolset and run, but I think it would be likely 25-50x slower.

One of the use cases I've wondered about for AI is giving it a picture of the "spice wall" in a grocery store and asking it to draw a pelican on a bicycle. Can you run this on a 36GB MacBook Pro (M3 Pro)? What would be a good guard on websites to use it as another content protection layer.

By the way, just want to drop a model into their existing toolset and run, but I think there are a lot of ways to deal with the pain of multiple bones crushing. It won't satisfy the people who are trying to pretend that LLM text was something they wrote themselves are probably too lazy to put in the work to try and defeat it anyway. Some here are arguing that mechanisms used by LLM producers during training to optimize the "think" chunk quality. I cannot remember any good articles about it now.