o1 Pro Mode – Full Analysis (plus o1 paper highlights) Artwork

AI Explained Official Podcast

Covering the biggest news of the century - the arrival of smarter-than-human AI. From the author of Simple Bench, which reveals the remaining gap between LLM and human reasoning. Hype-free, and the British accent is a freebie bonus.

All Episodes

AI Explained Official Podcast

o1 Pro Mode – Full Analysis (plus o1 paper highlights)

December 05, 2024 • Philip - Host of AI Explained YT • Season 1 • Episode 6

Oh boy. o1 pro mode out on the same night as o1 full. I read the 49 page paper, ran my own tests, spent my fuel allowance on Pro Mode and will give you all the highlights. Suffice to say the story is not as simple as it first appears.

Weights and Biases’ Weave: wandb.me/ai_explained

Plus, GPT-4.5? MLE Bench, Simple Update, Image Analysis and much more

o1 System Card: https://cdn.openai.com/o1-system-card-20241205.pdf

Apollo Research: https://www.apolloresearch.ai/research/scheming-reasoning-evaluations

Altman Tweet: https://x.com/AnonCEOMakeItAi/status/1864763052622504344

ChatGPT Pro: https://openai.com/index/introducing-chatgpt-pro/

Tibor Blaho: https://x.com/btibor91/status/1864709670470066605

Simple-bench.com

00:00 - Introduction

00:27 - ChatGPT Pro is $200

01:25 - OpenAI Benchmarks

03:20 - o1 System Card, o1 and o1 Pro Mode vs o1-preview

06:18 - Simple Bench surprising results on sample

08:31 - Weight & Biases

09:05 - Image Analysis Compared

12:51 - More Benchmarks and Safety