Загрузка видео...

Не удалось загрузить видео

На главную

This is madness... OpenAI o1 model builds a fully functional "chess game" that allows me to compete against an AI-based opponent. o1-preview is the real deal.

633,831 просмотров • 1 год назад •via X (Twitter)

Комментарии: 10

Фото профиля Haider.
Haider.1 год назад

it's a damn good model:

Фото профиля Tunc Yalgin
Tunc Yalgin1 год назад

Finally a non-snake game coding example. Looks amazing.

Фото профиля Haider.
Haider.1 год назад

Lmao, I believe it's also a common game, but what sets it apart is the competition between AI & human.

Фото профиля Boris Power
Boris Power1 год назад

hm... Nc6 is strange for a minmax algorithm, since it looses a piece on e4

Фото профиля Haider.
Haider.1 год назад

I think situations like this really highlight the difference between human and computer chess understanding. we might see Nc6 and instantly recognize the danger, relying on pattern recognition and experience. the engine, on the other hand, might be focusing on a narrow set of calculations and miss the bigger picture.

Фото профиля realSpaceKangaroo
realSpaceKangaroo1 год назад

I built this months ago in 4o, and mine has the 2 ai's play against each other. o1 can do it in less prompts but its not some emergent capability...

Фото профиля Kris Lukanov
Kris Lukanov1 год назад

This is one of the tests that AI models were failing to build up until now. #o1 is truly amazing at coding!

Фото профиля Haider.
Haider.1 год назад

I'm blown away, it took me almost 8-10 minutes. Question is: Are we (devs) going to replace it in the future?

Фото профиля Jason W
Jason W1 год назад

I can do this in seconds, with a quick search and a ‘git clone’. How much novel programming is it really doing? A better test would be to create something truly novel

Фото профиля Sebastian Castillo
Sebastian Castillo1 год назад

What is mad about it? Chess code is probably the more common code out there in public internet. My hard disk can also give you that code. PHD level hard disks !

Похожие видео

OpenAI just announced API access to o1 (advanced reasoning model) yesterday. I'm delighted to announce today a new short course, Reasoning with o1, built with OpenAI, and taught by Colin Jarvis, Head of AI Solutions at OpenAI, to show you how to use this effectively! Unlike previous language models which generate output directly, o1 “thinks before it responds,” and generates many reasoning tokens before returning a more thoughtful and accurate response. It is great at complex reasoning -- including planning for agentic workflows, coding, and domain-specific reasoning in STEM fields like law. But how you should use it is quite different from other LLMs. I think o1 will be a game changer for many AI applications; and in this course, you'll learn how to use it effectively. In detail, you’ll: - Learn to recognize what tasks o1 is suited for, and when to use a smaller model, or combine o1 with a smaller model - Understand the new principles of prompting reasoning models: Be simple and direct; no explicit chain-of-thought required; use structure; show rather than tell - Implement multi-step orchestration in which o1 plans, and hands tasks over to gpt-4o-mini to execute specific steps; this illustrates a design pattern to optimize intelligence (accuracy) and cost - Use o1 for a coding task to build a new application, edit existing code, and test performance by running a coding competition between o1-mini and GPT 4o - Use o1 for image understanding and learn how it performs better with a "hierarchy of reasoning," in which it incurs the latency and cost upfront, preprocessing the image and indexing it with rich details so it can be used for Q&A later - Learn a technique called meta-prompting, in which you use o1 to improve your prompts. Using a customer support evaluation set, you'll iteratively use o1 to modify a prompt to improve performance You'll also learn about how OpenAI used reinforcement learning to produce a model that uses "test-time compute" to improve performance. I think you'll find this course enjoyable and valuable. Please sign up for it here:

Andrew Ng

357,661 просмотров • 1 год назад