Everyone is sleeping on few-shot prompts They're coming back, in a big way
AI
-
Claude 3 Opus excels with high-quality prompt engineering examples
By
–
Claude 3 Opus + 10 examples is ridiculously capable. Just make sure the examples are super high-quality. Garbage in, garbage out.
-
Claude 3 Models Excel at Handling Multiple Examples
By
–
Newer models like Claude 3 are quite good at handling many examples gracefully
-
Multi-shot Prompting Set for Major Resurgence
By
–
Multi-shot prompting is going to come back, in a big way
-
AI-Generated Election Misinformation: Rules Easily Manipulated
By
–
It turns out rules designed to prevent fake election-related images are easy to manipulate. @StanfordHAI
’s Daniel Zhang (
@dzhang105
) emphasized the importance of independent fact-checkers & third-party organizations in curbing AI-generated misinformation. -
Model Preview Assessment: Tuning and Performance Evaluation
By
–
I will say it doesn’t feel as tuned yet as other models, it is very much a preview, so it is hard to judge directly.
-
Gemini 1.5 Pro Outperforms Gemini 1.0 Ultra with Massive Context
By
–
Gemini 1.5 Pro is a very good model, by the way. Appears to beat Gemini 1.0 Ultra which was itself GPT-4 class on the stats. Also impressive that Google can more widely release massive context windows. Google seems to be moving quickly.
-
Ludwig Tutorial: Fine-tuning Mistral for Customer Support Intent Classification
By
–
New #LLM tutorial from the @ludwig_ai community: Streamlining Customer Support! Check out this blog from Ludwig hackathon winners, Divyansh Mishra, Abhishek Kaushik and Ankit Patil to hear how they fine-tuned #Mistral for intent #classification. https://
pbase.ai/43ArJgg -

Nvidia B200 GPU plotted on Moore’s Law chart
By
–
By popular demand: Nvidia B200 plotted on our Moore's Law chart. It's pretty big for a GPU. But kinda small when you're used to wafer scale.
-

NVIDIA Launches AI Microservices for Generative Copilots
By
–
New AI microservices for developers to create and deploy #generativeAI copilots across NVIDIA CUDA GPU-installed base. Just announced at #GTC24 Check out the press release to learn more > https://
nvda.ws/3x9kK1K