LLMTest_NeedleInAHaystack VS SillyTavern

This research follows the “haystack test” Greg Kamradt published when the update GPT-4 came out (twitter, code). That test provided useful insight into (the lack of) context recall performance. But it was performed on a very small sample test (limiting its statistical significance) and was initially limited to GPT-4 (he has since published an updated version that also uses Claude 2.1). Moreover, the test data consists of essays that were likely already used pretraining LLMs, and the results were evaluated by GPT-4, potentially introducing confounding variables into the mix.

Right, but it's certainly easier for people who might not even know what "API" stands for, and that's quite nifty. As far as self-hosted frontends go, I can personally recommend SillyTavern[1] in the browser, ChatterUI[2] on mobile, and ShellGPT[3] for CLI. LobeChat looks pretty cool, though! I'll definitely check it out.

[1] https://github.com/SillyTavern/SillyTavern

[2] https://github.com/Vali-98/ChatterUI

[3] https://github.com/TheR1D/shell_gpt

I don't think there is any enumeration for {{char}} macros. Here is some good discussion on the subject.

As for SillyTavern, you need the main SillyTavern frontend and SillyTavern-extras (for TTS, STT, etc.) They're pretty easy to install. SillyTavern connects to oobabooga and SillyTavern-extras via API.

Finally, no matter what backend I use, I need it to be compatible with my power-user frontend, SillyTavern. That way I always use the same UI, with the characters I created and extensions I want, e. g. web search, XTTS text-to-speech and Whisper speech recognition for real-time voice chat - and all of that local!

SillyTavern v1.10.5 frontend (not the latest as I don't want to upgrade mid-test)