Don’t forget to check out our Co-founder and CEO @aidangomez
’s panel with Jensen Huang @NVIDIA and his co-authors of the seminal paper, “Attention is All You Need” on March 20 at 11:00 am PDT.
LLMS
-
Aidan Gomez Panel with Jensen Huang on Attention Mechanism
By
–
-
NVIDIA Announces RAG-Optimized Command-R Model for Production
By
–
Just announced @NVIDIAGTC
! Our RAG-optimized Command-R model, designed for businesses to get into large-scale production, is coming to the NVIDIA API catalog. -
NVIDIA NIM Integration for GPU-Optimized LLM Inference in RAG
By
–
Our Integration With NVIDIA NIM for GPU-optimized LLM Inference in RAG As enterprises turn their attention from prototyping LLM applications to productionizing them, they often want to turn from third-party model services to self-hosted solutions. We’ve seen many folks
-
NVIDIA NeMo Microservices Enable Enterprise Generative AI Solutions
By
–
Unlock the power of #generativeAI with new NVIDIA NeMo microservices. Deliver enterprise-ready models with precise data curation, cutting-edge customization, retrieval-augmented generation (#RAG), and accelerated performance. https://
nvda.ws/4cmvxFJ -
Building Code Agents: Programming AI Software Engineers
By
–
Webinar Wednesday 3/20: Building Code Agents! Sign up here https://
crowdcast.io/c/codeagents Agents that write and run code are powerful, as Cognition Labs showed with their recent release of Devin, the "AI SWE". But they are complex to program, hard to deploy, and even harder to -
Prompt Engineering Still Matters Despite Premature Obituaries
By
–
All the people who said 'RIP prompt engineering' trying to get good results from their LLMs https://t.co/ofZraLdpVK
— Rob Lennon 🗯 | AI Whisperer (@thatroblennon) 18 mars 2024All the people who said 'RIP prompt engineering' trying to get good results from their LLMs
-
Parallel Haiku API Calls Script Optimization
By
–
Modified the script to run the Haiku calls in parallel. Much faster now!
-
Analyzing the architectural approach of AI agents like Devin
By
–
Wondering if “Devin” approach will make it work better smith like a combination of LLMs with an access to search which can keep enhancing its own knowledge base more precisely to the context
-
Smaller Models Handling Smaller Tasks in AI Systems
By
–
Yeah that's why the smaller model is doing the smaller tasks
-
Claude’s Full Output Thinking Process Saved and Analyzed
By
–
This is the full output saved as a text file, it's fascinating to see how Claude thinks. The whole process took exactly 13 minutes and 20 seconds.