Viewing profile — hardchaos

this is super cool, the named regions are a nice touch!

"In this paper, we show both theoretically and empirically, that these state-of-the-art detectors cannot reliably detect LLM outputs in practical scenarios." This was my finding as…

Most people do not build/train large models locally - if you get to that point, you'll be renting cloud compute. Any computer that has a GPU and is within your budget is good to ge…

This is my experience too, regularly used XM4’s the past year, and tinnitus is no better/worse, as far as i can tell.

Hello everyone! I made Chippy for my discord server a few months ago and it has now been updated to support ChatGPT (gpt-3.5-turbo) and threads. Please feel free to let me know abo…