Use cases for encoder LLMs (classification) & decoder LLMs (chatbots) are obvious. Seq2seq tasks like translation, where it makes sense to have access to the whole input, is where it gets interesting.
Re encoder-decoder LLMs (eg T5): Is there still a benefit of using an encoder?
LLMS
-
Encoder vs Decoder LLMs: Benefits for Seq2Seq Tasks
By
–
-
Advanced Retrieval Tools: Smart Splitting, Self-Query, Agents
By
–
Deep dive on retrieval Excited to have the opportunity to talk about the advanced retrieval tools we're building: – smart text splitting
– self-query
– retrieval agents Even more excited to be joined by @UnstructuredIO @trychroma
… should be fun -
Scaling LLM Performance: Token-Crisis Solutions and Diminishing Returns
By
–
They actually might be doing this already but yeah, probably diminishing returns.
Some insights in the "To Repeat or Not To Repeat: Insights from Scaling LLM under Token-Crisis" paper: https://
arxiv.org/abs/2305.13230 -
AI Watermarking Labels Indigenous Rights FPIC Regulation
By
–
I’m wondering if you feel your amazing Labels could be used for the “watermarking” we all know will not utilize sovereign indigenous or FPIC to “regulate” AI / LLMs? Your labels are so specific, impactful & inspirational & should be the model for labeling writ large for AI.
-
Understanding: Human Intelligence vs Large Language Models
By
–
Ingredients of Understanding A nice article by @dileeplearning about how human understanding is different from LLM “understanding” https://
dileeplearning.substack.com/p/ingredients-
of-understanding
… -
Emergent Abilities in LLMs: Responding to LeCun’s Critique
By
–
Yann LeCun is obviously a legend but I found this tweet to be quite misinformed. The whole point of "emergent abilities" such as few-shot prompting and chain-of-thought prompting, is that we clearly *did not* explicitly train or fine-tune them into the model. These abilities
-
AI Progress Accelerating: Capabilities, Compute, and Data Surge
By
–
The coming wave IS coming. Progress is not slowing but speeding up. This piece makes that crystal clear. Capabilities, compute, data… Everything is going up. These patterns are deep and relentless. https://
time.com/6300942/ai-pro
gress-charts/
… -
Chat with Data Anywhere Using LangChain and Ibis
By
–
LLMs unlock capabilities for organizations to chat with data. But what if you want to chat with or ask questions of your own data, stored in different sources? Today we show how to use @langchain and @IbisData. https://
voltrondata.com/resources/use-
langchain-ibis-chat-with-data-stored-anywhere
… -
Advanced Retrieval Webinar with LangChain, Chroma, Unstructured
By
–
Advanced Retrieval Webinar @langchain x @trychroma x @UnstructuredIO Retrieval is a key part of most GenAI systems. And there is a lot of nuance to it! Excited to bring together some leaders from across the stack to discuss it live next week!
-
Context Window Challenges in Large Language Models
By
–
Can Large Language Models effectively use knowledge in their input context? Find out more in our blog post: 'Information Overload: Challenges of Expanding Context Windows in LLMs' https://
samaya.ai/blog@nelsonfliu Ashwin Paranjape @MicheleBevila20 @Fabio_Petroni @maithra_raghu