-
chain-of-thought-hub
Benchmarking large language models' complex reasoning ability with chain-of-thought prompting
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
-
text-generation-webui
A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
It's not just you. Here's a bit of research you can cite:
> GPT-4 from its website and Bubeck et al Mar 2023. Note that the version that Bubeck uses is GPT-4 Early which is supposedly to be more powerful than GPT-4 Launch (OpenAI paid a lot of alignment tax to make GPT-4 safer).
https://github.com/FranxYao/chain-of-thought-hub
Anecdotally, there seemed to be a golden set of weeks in late April to early May that seemed like "peak GPT" (GPT-4), followed by heavy topic and knowledge mitigation since, then -- just this week -- adding back some "chain of thought" or "show your work" ("lets go step by step" style) for math. I say anecdotally because I could just be prompting it wrong.
I noticed that it tries to forward the User to external Sources more (Answering Query, and then "For further Info, just ask an Expert"), or tries to get the User to do the Work (Here is a nice Overview of the Program, now you do the rest of the coding).
If i don't want the RLHF to get in my Way, i switch over to the API (sadly not the 4.0 one).
I also noticed a decline in following Instructions, i have a Primer i am preseeding my Chats with.
The Primer ends with "Do you understand? [Y|N]", and ChatGPT 3.5 usually answered with a Summary, ChatGPT 4.0 in the beginning just wrote "Y".
Now it behaves like 3.5, answering with a Summary instead of a "Y". Adjusted the Prompt to -> "Confirm instructions with a short and precise "Ok"." which seems to work.
Used Primer: https://github.com/Kalabint/ChatGPT-Primer
My recommendation would be to start with https://github.com/oobabooga/text-generation-webui
You will find almost everything you need to know there and on 4chan.org/g/catalog - search for LMG.