Friday, September 13, 2024

OpenAI releases new o1 reasoning model

 OpenAI releases new o1 reasoning model - The Verge

The rumored ‘Strawberry’ model is here, and the company says it can handle more complex queries — for a steep price. 

I was Wrong About ChatGPT's New o1 Model (youtube.com)

10 reasons why AI may be overrated : Planet Money : NPR

What is Chain of Thought (CoT) prompting and how does it compare to traditional prompting?

Chain of Thought (CoT) prompting is a technique used in artificial intelligence to enhance the reasoning capabilities of language models. It involves breaking down complex tasks into a series of intermediate reasoning steps, guiding the model to think through the problem step-by-step before arriving at a final answer¹².

Here's a simple example to illustrate this:

**Without CoT Prompting:**

- **Question:** I went to the market and bought 10 apples. I gave 2 apples to the neighbor and 2 to the repairman. I then went and bought 5 more apples and ate 1. How many apples did I remain with?

- **Answer:** 11 apples (incorrect).

----

**With CoT Prompting:**

- **Question:** I went to the market and bought 10 apples. I gave 2 apples to the neighbor and 2 to the repairman. I then went and bought 5 more apples and ate 1. How many apples did I remain with? Let's think step by step.

- **Answer:** First, you started with 10 apples. You gave away 2 apples to the neighbor and 2 to the repairman, so you had 6 apples left. Then you bought 5 more apples, so now you had 11 apples. Finally, you ate 1 apple, so you would remain with 10 apples (correct).

By prompting the model to "think step by step," CoT helps ensure that no intermediate steps are skipped, leading to more accurate and logical responses¹².

Source: Conversation with Copilot, 9/16/2024

(1) Chain-of-Thought Prompting | Prompt Engineering Guide. https://www.promptingguide.ai/techniques/cot.

(2) What is Chain of Thoughts (CoT)? | IBM. https://www.ibm.com/topics/chain-of-thoughts.

(3) What is Chain of Thought Prompting? Optimize LLM Results - Graphable. https://www.graphable.ai/blog/chain-of-thought-prompting/.

(4) Chain-of-Thought Prompting: Step-by-Step Reasoning with LLMs. https://www.datacamp.com/tutorial/chain-of-thought-prompting.