Fixing RAG with GraphRAG

LLMs improve writing-based knowledge work

Co-intelligence: book review

Winning prompt! $10k LLM reasoning challenge

$10k for LLM reasoning

LLM agents do software engineering

LLM benchmarks

LLMs eat entry-level SWEs

LLMs can debug with prints

Determinism ⇒ Fast LLMs (Groq)

Self-discovery: Choosing the Best Prompt for the Problem

Asleep at the wheel: can AI reduce performance?

The Future of RAG in the Age of Large Context Windows

GPT-4 passed the Turing Test!

CS higher ed in North America: all the stats you should know

I remember @AndrejKarpathy 's deleted tweet

LLMs for real world knowledge work

Watch me build a GPT for journaling

LLMs can "breed" their own prompts

LLMs with infinite context?

Can prompt engineering beat fine-tuning?

Can LLMs discover new math and CS?

How will CS educators adapt to AI tools?

How does Copilot do on advanced CS courses?

Fine-tuning Language Models for Factuality

OpenAI Retrieval-augmented generation (RAG) API

Understanding Retrieval Augmentation for Long-form Question Answering

Hurdles in Long-form Question Answering with LLMs

Chain of Thought with Retrieval for LLMs

Prompting is Programming