o1-mini making a @Gradio demo to use o1-mini
LLMS
-

OpenAI Releases o1: Advanced Reasoning Model with Improved Safety
By
–
Finally o1 is out – our first model with general reasoning capabilities. Not only it achieves impressive results on hard, scientific tasks, but also it gets significantly improved on safety and robustness. https://
openai.com/index/learning
-to-reason-with-llms/
… We found reasoning in context about safety -
o1-preview and o1 Models Coming to ChatLLM Soon
By
–
We should have o1-preview and o1 on ChatLLM in a couple of hours
-
User comparison of GPT-4o performance
By
–
Not much different from 4o in many of my use cases to be honest.
-

The ‘strawberry’ prompt as a viral LLM benchmark
By
–
LoL, how many rs in strawberry is now a suggested conversation starter
-
OpenAI o1 translates a corrupted sentence
By
–
8/ OpenAI o1 translates corrupted sentencepic.twitter.com/ztGzhlW7CA
— God of Prompt (@godofprompt) 12 septembre 20248/ OpenAI o1 translates corrupted sentence
-
Economics Capabilities of OpenAI o1 Model
By
–
6/ Economics with OpenAI o1
— God of Prompt (@godofprompt) 12 septembre 2024
What can this new model do in "Economics"?pic.twitter.com/MEU0MNC2Hg6/ Economics with OpenAI o1 What can this new model do in "Economics"?
-
OpenAI o1 solves a logic puzzle
By
–
3/ OpenAI o1 solves a logic puzzlepic.twitter.com/1hrMpoWO70
— God of Prompt (@godofprompt) 12 septembre 20243/ OpenAI o1 solves a logic puzzle
-
Researching or answering tricky questions with OpenAI o1
By
–
2/ Researching or answering tricky questions with OpenAI o1pic.twitter.com/CNM7coXRtw
— God of Prompt (@godofprompt) 12 septembre 20242/ Researching or answering tricky questions with OpenAI o1
-
OpenAI o1: ChatGPT now thinks before responding, codes video game
By
–
This is wild.
— God of Prompt (@godofprompt) 12 septembre 2024
OpenAI just dropped o1, also known as Project Strawberry 🍓.
Now ChatGPT thinks before responding.
10 wild demos from OpenAI:
1/ OpenAI o1 codes a video game from a prompt:pic.twitter.com/09ivpfe8M7This is wild. OpenAI just dropped o1, also known as Project Strawberry . Now ChatGPT thinks before responding. 10 wild demos from OpenAI: 1/ OpenAI o1 codes a video game from a prompt: