?? Experimenting with OpenAI’s Code Interpreter
Exponential View via Midjourney

?? Experimenting with OpenAI’s Code Interpreter

Just coming back from holiday,? Nathan Warren was feeling a bit lazy and decided to try out Code Interpreter for the Sunday chart for our weekly newsletter.

No alt text provided for this image

He set it the task of comparing the?MMLU Benchmark, a common LLM yardstick, with?ChatbotArena, a crowd-sourced, random chatbot battle platform.

In under 3 minutes, I loaded up a CSV file and let GPT-4 visualise and fish out the prime nuggets from the data. It managed to glean the core insights, that there was a positive link (r2=0.854) between the benchmarks, and that private models tend to outdo open-source on both benchmarks. As someone who doesn’t code every day, I estimate that without Code Interpreter this would’ve taken me around 30 minutes.

It is a groundbreaking tool. Back in February, I delved into how?ChatGPT empowers users with a tool that offers deep dissection of particular problem sets, all for a modest monthly fee. Back then, it could only deal with text inputs. Now, with the birth of the Code Interpreter, it can deal with data. Its speed and accessibility are truly impressive, and that gives it revolutionary potential. See our quarterly overview of AI from earlier this week where we?shared a paper looking into the long-term impact of AI on data science.?

But like many revolutions, this one often falls short of accurately hitting its target. Code Interpreter turns every person into a data analyst without training them as a data analyst. Data can be scrutinised through multiple lenses, some more accurate than others. Unless the people using it have a thorough understanding of analytical methods, Code Interpreter could inadvertently contribute to the propagation of misinformation. Yes, it’s a powerful tool, but proceed with caution – and validate your outputs!

Let me know in comments: Have you tried out Code Interpreter? If so, what did you think?


Latest posts

If you’re not a subscriber, here’s what you missed recently:

  1. ??? Three months of AI in six charts?
  2. ???The eye of the needle: Making sense of Threads
  3. ???Promptpack: Generative AI for exponentialists


Syed R.

Distinguished Engineer @ Verizon | MBA, Network API, Edge Computing

1 年

I tried code interpreter and totally amazed by its capabilities. With few prompts it performed all the data cleaning, merging, exploration, regression modeling and interaction variable analysis. Something that took me few hours in R tool .. it did all of that in few minutes. In addition, it provided reasonable analysis. However, i found that it didn't catch the missing data in one of the files, and i had to explicitly mention and upload the new file. Here is the link of the analysis https://chat.openai.com/share/384686e0-9a2b-48a6-a87b-a0a8a769f68d

回复
Dan Wong

Digital Transformation | AI Change Management | Innovation | East & West Collaboration

1 年

Azeem Azhar It’s absolutely amazing how quickly these changes are happening. You were quite prescient in your observation that we are now living in The Exponential Age.

要查看或添加评论,请登录

社区洞察

其他会员也浏览了