We are introducing OpenAI o1, a new large language model trained with reinforcement learning to perform complex reasoning. o1 thinks before it answers—it can produce a long internal chain of thought before responding to the user.
Timestamp
00:00 Intro
00:05 Is this Strawberry?
00:40 What is OpenAI o1?
01:49 Different types of o1 Models
05:25 o1 Solving Figuring out Encryption example
09:00 OpenAI o1 Metrics
12:37 Why o1 is not the right model all the time?
13:15 How o1 reasoning works?
15:35 OpenAI o1 API Code
🔗 Links 🔗
https://openai.com/index/learning-to-reason-with-llms/
API Docs – https://platform.openai.com/docs/guides/reasoning?reasoning-prompt-examples=research
My old Reflexion Video – https://www.youtube.com/watch?v=yHouKDbiPPs
❤️ If you want to support the channel ❤️
Support here:
Patreon – https://www.patreon.com/1littlecoder/
Ko-Fi – https://ko-fi.com/1littlecoder
🧭 Follow me on 🧭
Twitter – https://twitter.com/1littlecoder
Linkedin – https://www.linkedin.com/in/amrrs/
source