GENERATIVE AI

→ View original post on X — @nvidia

New AI Inference Microservices for Multi-Platform Model Deployment

By

@nvidia

–

20 March 2024 22h00

Announced at #GTC24, new inference microservices that transform the way you deploy #AI models across diverse platforms including cloud, data center, and workstation.

→ View original post on X — @langchain

Is RAG Dead With Million Token Context Windows?

By

@langchain

–

20 March 2024 21h57

LangChain x @TimescaleDB Webinar: Is RAG Really Dead?! With the advent of LLMs with context windows of 1 million tokens (like Google Gemini), many have declared the utility of Retrieval Augmented Generation dead and no longer necessary. But is this actually true? Or simply

AI System Shows Notable Improvements in Performance Capabilities

By

–

20 March 2024 20h19

It’s noticeably better, smarter, more thorough and malleable

Direct API usage over LLM frameworks for faster development

By

–

20 March 2024 20h06

The reason I can work so fast is simple: I use no LLM frameworks, just hit the APIs directly for what I need. Frameworks are a time-suck. That, and I use Claude as an engineering assistant. While I’m working on writing a prompt or integrating some code, I’ll simultaneously have

Claude 3 Instance Evaluates Multiple Outputs Decision Making

By

–

20 March 2024 20h04

A separate Claude 3 prompt instance is shown the two outputs, the task description, inputs, etc., and can make a decision from there. Lots of ways to make this more robust.

→ View original post on X — @nvidiaai

NVIDIA SAP Partnership Accelerates Enterprise Generative AI Capabilities

By

@nvidiaai

–

20 March 2024 20h00

See how NVIDIA and @SAP are expanding their partnership to accelerate enterprise customers’ ability to harness the transformative power of data and #generativeAI with new and scalable capabilities. #GTC24 https://
nvda.ws/3INbKBQ

Building AI Tools Efficiently: Prompt Engineering Best Practices

By

–

20 March 2024 19h46

I actually spend way less time on things like this than you might think! The whole claude-prompt-engineer buildout took less than 30 minutes last night. Did it while cooking dinner. After building with AI for a while, it becomes second nature 🙂