OpenAI released its o3-mini model exactly one week ago, 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,” and here’s why it matters.
The update
OpenAI announced via an X post that free and paid users would now be able to view the reasoning process the o3-mini goes through before arriving at a conclusion. For example, in the post, a user asked, “How is today not a Friday?” and under the dropdown showing how long it took, the model delineated every step in its chain of thought that allowed it to land on its answer.
Understanding how the model arrived at the conclusion is helpful because it not only helps users verify the accuracy of the conclusion, but it also teaches users how they could have arrived at that answer themselves. This is particularly useful for math or coding prompts, in which seeing the steps could allow you to recreate them the next time you encounter a similar problem.
Also: OpenAI launches new o3-mini model – here’s how free ChatGPT users can try it
Paid ChatGPT subscribers will also be able to see the updated chain of thought in o3-mini in the “high reasoning” effort. As the name implies, “high reasoning” just allows the model to apply more compute power for more advanced questions that require higher reasoning.
What is 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?
In the same way you would ask a person to explain their reasoning step by step, 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.
Also: OpenAI eyes the wearables business: Robots, headsets, watches and a whole lot more
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.
o3-mini is exceptionally great, but I do worry that summarized chain-of-thought is actually worse than nothing at all.
True CoT exposure acts as a prompt debugger. It helps us steer the model.
Summarized CoT obfuscates this and potentially adds errors – makes it hard to debug. https://t.co/cgz6ONCkvk— Mckay Wrigley (@mckaywrigley) February 6, 2025
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.
How to access
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.
Also: From zero to millions? How regular people are cashing in on AI
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.
Source link
#OpenAIs #o3mini #lets #AIs #thought #process
