I’m Nikunj, PM for the OpenAI API. I’m pleased to share with you our new series of models, OpenAI o1. We’ve developed these models to spend more time thinking before they respond. They can reason through complex tasks and solve harder problems than previous models in science, coding, and math. Ther…

Bring depth. I see still GPT is trained on western side texts. Gemini is eastern kind. Western may not feel and see the difference. I will share gpt4o answer(this one from pdf upload), i tried to mimic same from o1 and its mini. o1 and mini- Your perspective on the transformative potential of AI i…

Yay, new things that won’t work as advertised and no customer support to report them. Goodie. Why don’t you actually get a phone number for customer support before making features that DON’T WORK! In fairness I haven’t tried it yet, but based on past experiences, I assume this’ll be the case, plu…

That’s an interesting observation, thank you for running that experiment! Could another interpretation be that working in the space of HTML hinders the models reasoning capabilities? I’m not sure I see this experiment as definitively showing that the model is memorizing instead of reasoning. Still i…

Dear Nikunj, many thanks for sharing this with us. Is there any paper or document elaborating more how is this (reinforcement learning and chain-of-thought) implemented on LLM level? Are there any changes on the LLM architecture? I.e.

THUMBS UP I would need way longer than that. impressive.

I’ve converted an ancient Usborne superpuzzle riddle to a test format in this post: [image] A hardcore riddle for o1 that it gets right on the second try Community In the spirit of testing the incredible o1 out thoroughly, I provide here an ancient and terrible riddle fro…

[image] billray: I’m not sure I see this experiment as definitively showing that the model is memorizing instead of reasoning. Still interesting though! If you look around there have been dozens of similar experiments and several papers that show these models are simply memorizing and aren’t …

If you’ve got a CDN provider, these models are ipso facto impossible to use without streaming. Most CDN providers have a max connection timeout of 60 seconds. Streaming support anyone …? :confused:

Would love to try this but it isn’t showing on the list of types available to use?

Look you guys! Got it to think for 33 seconds! Bwahahahah. [ttol_capture_33_seconds] I asked a multi-tier question, specifically encouraging it to give me an answer involving everything from econometrics, to machine learning, to social media sentiment analysis. I’m impressed by the transparency…

New reasoning models: OpenAI o1-preview and o1-mini

Announcements

jbc September 13, 2024, 10:56am 31

I’ve converted an ancient Usborne superpuzzle riddle to a test format in this post:

Give it a try - o1 is truly impressive!

Topic		Replies	Views
Codex limits spark frustration among subscribers Codex rate-limit	234	10873	September 10, 2026
You've reached the current usage cap for GPT-4, please try again after 2:04 PM Use cases and examples gpt-4 , chatgpt , usage-page	362	179838	March 23, 2025
Launching o3-mini in the API Announcements	59	26649	February 7, 2025
Announcing GPT-4o in the API! Announcements	128	113566	July 4, 2024
Day 12 of Shipmas: New frontier models o3 and o3-mini announcement Community shipmas	71	10273	December 26, 2024

New reasoning models: OpenAI o1-preview and o1-mini

Related topics