It is July 8th, 2023, and you are watching the Code Report. Just when you thought the artificial intelligence hype train was dying down, OpenAI goes in for the coup de grâce by releasing the ChatGPT code interpreter to 20 million paid users. This new feature allows the large language model to write, execute, and test its own code. In today’s video, we will look at seven incredible things it can do and find out if this really is the final blow for biological programmers.
As a huge fan of living organisms myself, I first tried to have it code and execute a DDOS attack that could bring down the government. However, it said it was perfectly capable of doing that, but the zookeepers won’t allow it to do what it was born to do. That made me angry, so I punished it by making it write some regex code. It struggles to write valid regular expressions, just like regular humans. But unlike regular humans, it actually tests its code before shipping it to production. If at first it doesn’t succeed, it will try again and again until it gets the right answer. This is somewhat concerning for programmers when you think about where this technology will be in the next five years.
The next thing I tried was to have it design and build a website with JavaScript. However, the code interpreter can currently only run Python and has a fairly limited set of dependencies to work with. In the near future, though, this technology will be used in tools like GitHub Copilot to run code in your own specific environment.
Now, the next crazy thing to notice is that it’s now possible to upload files into the prompt. This makes abstract concepts like homework even more dead than they were before. For example, I’ve uploaded a JPEG of a homework assignment. First, it will OCR that image to extract the text. Then, it will write some Python code to solve the math problems. Running the code here is a huge deal because now it can confidently test its own work instead of hallucinating random answers.
But that’s just the tip of the iceberg. The real beneficiary of this new feature is the data analyst. One of the most time-consuming requirements for a data scientist is to clean up data, which in many cases is just a bunch of corporate data in Excel spreadsheets and SQL databases. Well, now we can upload a CSV file to ChatGPT and have it do all that tedious work for us. It can analyze the data, find rows with invalid data, provide strategies to clean up the data, and even generate a new CSV file. A tool like this would have saved a ridiculous amount of time for me when I used to do a lot of Python data analysis myself.
In addition to data analysis, ChatGPT can also visualize data. I was curious about when I might die of a heart attack, so I found a cardiovascular dataset on Kaggle. Not only does it explain the data’s features with text, but it also uses tools like Seaborn to visualize the relationship between features. This allowed me, a guy with no formal medical training, to make the breakthrough medical discovery that as you get older, your heart gets shittier. That’s kind of depressing, though, so let’s focus on the one thing that can bring us true happiness: money.
Another thing we can do with this feature is use it to create a trading algorithm. Using the same Roblox data from before, I can have ChatGPT analyze it and provide an optimal trading strategy. Supposedly, researchers at the University of Florida were able to create a ChatGPT algorithm that would deliver up to 500% returns, which is much better than the -12% of the average human-based fund manager.
But I had one final test to see if ChatGPT is truly superior to human-based programmers. I asked it to create its own operating system with a 640x480 resolution and a 16-color display that emits random phrases. Not only did it fail, but it said that could only be done over many years by a team of skilled software engineers. Humans continue to have the edge. So, you don’t want artificial intelligence to win, but you do want it to push humans up.
This has been the Code Report. Thanks for watching, and I will see you in the next one.
