I LOVE Claude Opus. I use it more than ChatGPT now… However, I still use ChatGPT often. I've built a handful of custom GPTs tailored to processes I do almost daily. That single element keeps me logging back into ChatGPT daily.
LLMS
-
DBRX General-Purpose LLM Now Available on Databricks Marketplace
By
–
#DBRX, a new general-purpose LLM, is now available on Databricks Marketplace! Enterprises can use DBRX in RAG apps or to build a DBRX-style MoE model with their own data. Check it out to advance your AI initiatives. https://
dbricks.co/43yPx3Q -
GPT-4 Vision and Claude 3 for OCR: Hallucination Concerns
By
–
Anyone been experimenting with GPT-4 vision / Claude 3 for OCR? Sending it an image of a scanned PDF and trying to get the text out? I tried it just now (with GPT-4) and I think it may have hallucinated most of the text, anyone else seen that before I really start digging in?
-
Google Gemini VertexAI JavaScript LangChain Integration
By
–
Google Gemini + VertexAI in JS We've revamped @googlecloud VertexAI support in LangChain.js with new partner packages! Gemini support Structured output/tool calling Support for web envs like @nextjs Huge s/o to @afirstenberg
! Docs below : -
Rundown University Workshop: Claude 3 Writing and AI Agents
By
–
The Rundown University has made a decision for the first workshop!
— Rowan Cheung (@rowancheung) 27 mars 2024
On Friday, we'll cover the basics of using Claude 3 to replicate writing and then explore deploying AI agents with Claude.
It'll be the best workshop on Claude 3 on the Internet. Join with the link below. https://t.co/19mROVxRBz pic.twitter.com/cR934Uajv5The Rundown University has made a decision for the first workshop! On Friday, we'll cover the basics of using Claude 3 to replicate writing and then explore deploying AI agents with Claude. It'll be the best workshop on Claude 3 on the Internet. Join with the link below.
-
AI Models Confuse Training Data with References Introspection
By
–
"The following is likely not entirely accurate, but the model tends to think that everything it knows about was in its training data, which it was not (sometimes only references were). So this produces more accurate accurate answers when the model is asked to introspect"
-
DBRX Instruct Model Repository Access Discussion
By
–
Neat – would that be in the https://
huggingface.co/databricks/dbr
x-instruct/tree/main
… repo? I couldn't spot it there -
RAG From Scratch: Query Structuring for Databases
By
–
RAG From Scratch: Query Structuring Our RAG From Scratch video series walks through impt RAG concepts in short / focused videos w/ code. This is the 11th video in our series and focuses on query structuring. Problem: We interact w/ databases using domain-specific
-
Preventing Hallucinations in Production LLM Systems
By
–
How can you prevent hallucinations and create more Robust LLM systems? As more and more LLM apps are put into production, the biggest problem to overcome is preventing hallucinations. Here are a couple ways to prevent hallucinations. We personally apply a variety of these