Daimon https://
x.com/sjwhitmore/sta
tus/1580593217153531908?s=20&t=D1cfJkJyC_MQveA1BiCpYQ
… a chat-based AI personal assistant with long-term memory about you. by @sjwhitmore
AI
-
Daimon: Chat-Based AI Assistant with Long-Term Memory
By
–
-
GPT-Index: Data Structures Powered by GPT-3 for Query Answering
By
–
GPT-Index https://
github.com/jerryjliu/gpt_
index
… GPT Index is a project consisting of a set of data structures that are created using GPT-3 and can be traversed using GPT-3 in order to answer queries. by @jerryjliu0 -
ThoughtSource: Open Resource for Chain-of-Thought Reasoning in LLMs
By
–
ThoughtSource https://
github.com/OpenBioLink/Th
oughtSource
… ThoughtSource is a central, open resource and community around data and tools related to chain-of-thought reasoning in large language models by @matthiassamwald -
Notion QA Bot: Have Conversations with Your Notion Database
By
–
Notion QA Bot https://
github.com/hwchase17/noti
on-qa
… Have a conversation with your Notion Database by @hwchase17 -
LangChain showcases favorite open source projects using framework
By
–
We recently added a page in our documentation highlight some of our favorite projects (with preference for open source) that use LangChain! https://
langchain.readthedocs.io/en/latest/expl
anation/cool_demos.html
… What other ones did we miss/should we feature? on some of the ones highlighted: -
Expedia Runs 600 Billion Predictions Yearly Using 70 Petabytes
By
–
Expedia, one of the world’s largest travel companies, sees data as their competitive advantage. It is running 600 billion predictions per year, analysing 70 PT of data. #AWS #reInvent
-
Text-davinci-002 RLHF tuning clue in InstructGPT announcement footnote
By
–
As far as I can tell, the only clue that that text‑davinci‑002 wasn't RLHF-tuned was this footnote in the InstructGPT announcement: https://
openai.com/blog/instructi
on-following/#fn2
… -
Is text-davinci-002 RLHF-tuned? A footnote suggests otherwise.
By
–
As far as I can tell, the only clue that that text‑davinci‑002 wasn't RLHF-tuned was this footnote in the InstructGPT announcement: https://
openai.com/blog/instructi
on-following/#fn2
… -
text-davinci-003 is first RLHF model, not 002
By
–
Also, it seems that the new text‑davinci‑003 is actually the *first* released model to incorporate RLHF tuning, using the PPO algorithm. I've been misdescribing text‑davinci‑002 as an RLHF model for the past year.