Beyond Benchmarks

Really Evaluating AI

Evaluating AI Agent Tool Selection

When you have a hammer (in the first position), everything looks like a nail

(Re-) Ranking RAG Solutions

5 lines of code -> better RAG

To Quantize or not to Quantize

Asking the right questions about quantization

Probing LLMs for a World Model

LLMs Aligned! But to what end?

What RL can and cannot do

Navigating the ML Content Maze: Strategies for a High-Quality Feed

Essential tips from Nathan Lambert's latest Interconnects post and our Practically Intelligent podcast.

Fashion Meets AI

Designing a Wedding Outfit with GPT-4

AIs Supervising AIs

AI Benchmarking - the good, the bad, and the confusing

Fine-Tuning LLaMA 2

A hands-on example of fine-tuning a Llama model

New Notebook to Fine-tune with OpenAI

Get the most out of Gen AI with fine-tuning