DEV Community

Mikhail Shevtsov
Mikhail Shevtsov

Posted on

OpenAI nextgen GPT

Cover

๐Ÿ“ Note:\
This article was generated using llama 3.1:8b model with help of
Ollama;\
Thumbnail was generated using Flux Schnell model with help of
ComfyUI;

The Future of Large Language Models: Introducing OpenAI's "o1" Series ๐Ÿš€

Watch the full video on our YouTube channel ๐Ÿ“น

As a tech enthusiast, I'm excited to share with you the latest development in the world of Large Language Models (LLMs). Yesterday, OpenAI, the company behind
ChatGPT, released a new series of "Thinking" models called "o1". In this article, we'll delve into what these models can do and why they're a game-changer for
the future of LLMs.

The Limitations of Traditional LLMs ๐Ÿค”

Traditional LLMs work by generating the most probable next token based on the input. This straightforward principle allows them to provide decent results, but
it's not without its limitations. For instance, when faced with complex questions or tasks, these models often struggle to provide accurate answers.

One classic example is the question "How many R letters in the word 'strawberry'?" ๐Ÿค” Traditional LLMs would typically answer 2, which is incorrect. To solve
this type of question, more advanced techniques such as a "Chain of Thoughts" are required.

Introducing OpenAI's "o1" Series ๐Ÿ”ฅ

The "o1" series models address these limitations by introducing "reasoning" tokens that are truncated from the output. This allows them to iterate over the
answer multiple times until they provide a well-thought-out response. The result is more accurate and contextually relevant answers.

Two distinct models are available: o1-preview and o1-mini. If you're using the API, these models can be accessed as part of your workflow.

Pricing ๐Ÿ’ธ

While the "o1" series is a significant upgrade over traditional LLMs, it comes at a price. The cost for using these models is higher than their predecessors:

  • $15.00 per 1 million input tokens and $60.00 per 1 million output tokens for o1-preview
  • $3.00 and $12.00 for o1-mini model

However, OpenAI plans to release the "o1" series for free ChatGPT users in the near future.

What's Next? ๐Ÿ”ฎ

The "o1" series is not a replacement for traditional LLMs but rather an addition that solves more complex tasks. In the world of Wiregate, we firmly believe that
such models will eventually replace all other simple models.

What are your thoughts on the future of Large Language Models? Share your opinions in the comments below! ๐Ÿ’ฌ

Want to learn more about this topic? ๐Ÿ”

Stay tuned for more updates on this topic! ๐Ÿš€

Source: https://blog.wiregate.io/posts/openai-nextgen-gpt

Top comments (0)