Stories by georgehill

FinanceBench: First benchmark for LLM performance on financial questions

Contrastive Chain-of-Thought Prompting

Elon Musk's X defends US university student in trouble over posts

How to Build a Defensible A.I. Startup

ChatGPT has 190 citations on Google Scholar

I've resigned from my role leading the Audio team at Stability AI

Yahoo Search to start rolling out in the first weeks of 2024

Mart: Improving LLM Safety with Multi-Round Automatic Red-Teaming

A Diverse and Multilingual Benchmark for Cross-File Code Completion

Galactica: A Year Later – Lessons from a Controversial Launch

Chat UX Is Great, but Wait Till You See Agent UX

My Company Died – Learn from My Mistakes

AI Search Is Turning into the Problem Everyone Worried About

Adversarial Attacks on LLMs

GPT4 turbo now tops AlpacaEval

Levels of AGI: Operationalizing Progress on the Path to AGI

How OpenAI is building a path toward AI agents

Grok-1 Outperforms ChatGPT-3.5 and Inflection-1 in Compute Class

9
10
11
12
13
14
15
16
17
18