The host conducted an in-depth test of OpenAI's newly released ChatGPT o1 model, comparing it to previous language models and putting it through a series of challenging tasks. The results demonstrate significant advancements in AI capabilities, with the o1 model outperforming its predecessors in various areas.
The host began by noting that OpenAI had used a question from his previous AI rubric on their official website, suggesting that the company may be paying attention to his work. He then proceeded to test the o1 model, which is available in two versions: ChatGPT o1-preview and o1-mini.
This is how we know we are rapidly moving to AGI.
The fact that our metrics do not work show we are entering something completely different.
yes, things are just moving faster and faster. I couldn't help myself and bought openai premium for a month just to try it out for myself.
Not surprisingly, it's very impressive
What is going to get very interesting is when Claude, Grok, and Llama have their next versions out.
Do you think OpenAI is going to be the only one forging ahead at such a pace?
I have a feeling neither Anthropic or Elon (or Zuckerberg for that matter) is about to let OpenAI win this race. I mean it wasn't long ago that Anthropic's latest model was stronger than GPT
Agreed.
No way they are sitting back. Elon is throwing a lot of compute at things to catch up. Meta is also getting a huge amount of GPUs also.