OpenAI Updates o3-mini Model with "Updated Chain of Thought"
What’s New?
Exactly one week ago, OpenAI released its o3-mini model, offering both free and paid users a more accurate, faster, and cheaper alternative to o1-mini. Now, OpenAI has updated the o3-mini to include an "updated chain of thought," which allows users to view the reasoning process behind the model’s conclusions.
Understanding Chain of Thought (CoT)
In the X post announcing the feature, OpenAI throws out the term "Chain of Thought," but what does it actually mean? CoT prompting encourages an LLM to break down a complex problem into logical, smaller, and solvable steps. By sharing these reasoning steps with users, the model becomes more interpretable, allowing users to better steer its responses and identify errors in reasoning.
How Does it Work?
To view the chain of thought, you do not need to do anything other than select the o3-mini model to answer your prompt. If you are a subscriber, you can select "o3-mini" or "o3-mini-high" from the model toggle dropdown in the upper left-hand corner. Once it is selected, any prompt you enter will automatically show its reasoning process. If you are a free user, all you have to do is click on "Reason" in the message textbox or regenerate a response to activate o3-mini. Once you do, you can just enter a prompt as usual and see the magic for yourself.
Why Summarized CoT?
Some reasons OpenAI could have chosen to go with its take on CoT are that it makes it easier for everyone to understand, and that exposing raw CoT could make the model more vulnerable to jailbreaking attempts.
Raw CoT vs. Summarized CoT
Raw CoT would display every intermediate step in real time as the model reasons through a problem. OpenAI’s take on CoT in this update is not raw, as it is summarizing the reasoning for users. This has caused many AI aficionados in the comments of the X post to express discontent with the feature, as raw CoT poses added benefits, such as how to better steer the model and troubleshoot incorrect reasoning.
Conclusion
The updated o3-mini model with "updated chain of thought" is a significant improvement, allowing users to better understand the reasoning behind the model’s conclusions. While some may be disappointed that it’s not raw CoT, the summarized version still provides valuable insights into the model’s thought process.
FAQs
Q: What is Chain of Thought (CoT)?
A: CoT prompting encourages an LLM to break down a complex problem into logical, smaller, and solvable steps.
Q: How do I access the chain of thought?
A: To view the chain of thought, select the o3-mini model to answer your prompt. If you are a subscriber, select "o3-mini" or "o3-mini-high" from the model toggle dropdown. If you are a free user, click on "Reason" in the message textbox or regenerate a response to activate o3-mini.
Q: Why did OpenAI choose to summarize CoT instead of exposing raw CoT?
A: OpenAI may have chosen to summarize CoT to make it easier for everyone to understand, and to avoid making the model more vulnerable to jailbreaking attempts.
