To get a sense of what I mean, try writing tweets with text-davinci-003. It’s remarkably difficult to get it to generate something that isn’t super generic, even with extensive prompting.
LLMS
-
Universities face bankruptcy due to AI, education to rely on LLM skills.
By
–
Would not be surprised if 1/3rd of universities go broke in the next 5 years because of OpenAI. A person's education and capability for knowledge work will trend towards being a perfectly correlated proportionality to their ability to utilize Large Language Models like ChatGPT.
-
Nearly 600 AI Tools Available Across 40 Categories
By
–
There are almost 600 tools on our site with 40+ categories for easy navigation
-
Microsoft invests 10 billion in ChatGPT partnership
By
–
Source: https://
semafor.com/article/01/09/
2023/microsoft-eyes-10-billion-bet-on-chatgpt
… -
Prompt Engineering’s Infancy: A Call for Advanced Tools and Syntax
By
–
Prompt engineering is in its infancy. We still prompt without syntax highlighting, like we’re stuck on POSIX vi. We have no linters, no type-checkers, no macros, no compilers, no syntax even for comments. There is room to grow.
-
ChatGPT Explained: Everything You Need to Know Simply
By
–
ChatGPT: Everything You Really Need to Know (In Simple Terms) Get the basics of #ChatGPT, the latest #AI-based #chatbot system that has taken the internet by storm.
-
Embeddings for semantic search in document context retrieval
By
–
im assuming by "using embeddings for context" you mean "using embeddings to do semantic search over a document store to select documents to insert into context"
-
Loading Different LLMs with Hugging Face Hub Integration
By
–
it should be easy, you can just load a different LLM and pass that in the same way an example huggingface hub notebook here: https://
langchain.readthedocs.io/en/latest/modu
les/llms/integrations/huggingface_hub.html
… -
ChatGPT generates satirical headlines about AI singularity
By
–
ChatGPT creates Onion headlines about the singularity
-
Crowdsourced Dataset of ChatGPT Errors for LLM Comparison
By
–
New project to compile a Q&A dataset of ChatGPT errors crowd-sourced from social media. Don't know of any dataset assembled adversarially like this against an LLM — feels valuable for future model comparisons: