I want to use ChatGPT as “interpreter” rather than “generative” AI

I don’t want ChatGPT to ghost write form me. I want to use it as “System 1.5”, as an assistant interpreter, rather than outsourcing my slowly and deliberately thinking “System 2” to it.

Bullshit generator

Closing his State of GPT conference presentation, Andrej Karpathy, one of the leading figures in AI development today, entertained his audience with an “inspiring” message generated by the platform:

His thought process might have been: if it’s called “generative” AI, the best way to demonstrate its capabilities is to let it generate something.

I don’t know about you, but to my taste this “inspire the audience” message is pure bullshit. Not a good selling point for me.

Prompt engineering

The presentation otherwise is very informative and enjoyable, explaining what ChatGPT does and how it is trained and fine tuned, and giving practical advice on prompting it to “think” step by step with instructions of the style “what would you tell a task contractor if they can’t email you back?”.

Thinking, Fast and Slow

The distinction between the two “systems” of human thinking, the fast, automatic “System 1” on one hand, and the slow, deliberate “System 2” on the other hand, introduced by Daniel Kahneman in his book Thinking, Fast and Slow, is a recurring topic of theorizing about what different AI systems do.

Here, Karpathy uses the analogy to explain his recommendation for the “Tree of Thought” method of “prompt engineering”, comparing the idea to tree search algorithms used in game-playing AI.

Do I want ChatGPT to think instead of me?

At this point, the conscious consumer awakens in me and asks: do I really want to outsource my “System 2” to ChatGPT? Or to any software for that matter?

There are some advantages of doing so:

• I can make it write an “essay” on “any topic” in no time.
• (Unfortunately no other advantage comes to my mind.)

On the other hand, why I write anything on any topic? There are a couple of reasons:

• I want to understand things better.
• I want to flex my reasoning and composing muscles.
• I want other people to understand things from a point of view, which is relevant at the same time for them and for me.

None of these points justifies using a shortcut instead of doing the work myself.

In fact, this conclusion is in line with Karpathy’s advice: I would never ask a task contractor (wether they can email back or not) to ghost write for me.

System 1.5, the “interpreter”

On the other hand, there are some cases when I want to comb through and interpret material which is not as well structured as I would like it to be. Understanding and structuring text is also flexing some muscles, but, just like lifting heavy objects, can require too much time and effort for the result.

So what if I thought about a “System 1.5” lying halfway through between “System 1” and “System 2”, working slowly but passively, doing the hard work of structuring and interpreting existing material produced by others?

It turns out that ChatGPT does a decent job with that, yielding the sweet spot for me. Let’s look at an example.

Creating a Deep Neural Network for sentiment analysis is an introductory exercise in Natural Language Processing. One popular training field is the IMDB review dataset in TensorFlow. The aim of the exercise is to classify movie reviews into positive and negative ones.

With ChatGPT we can do more.

Let’s look at a review about the Barbie movie (fell free to skip this version, later you will see a much more digestible version):

The first thing you need to know about Barbie is that Ryan Gosling is the best part of the entire film. For the duration he is over the top, dumb and hilarious. Every scene he was in had me laughing and I enjoyed just about everything he did in the film.

Margot Robbie is a great choice for Barbie and as usual puts in a fantastic performance. She hit pretty much every mark in my opinion and I can’t see anyone taking her place in this role.

Where the film falls flat unfortunately is not the characters, actors or even humour for that matter. It’s the incessant political lecturing.

It’s no surprise that this film takes a strong feminist angle. That’s to expected. Barbie was a doll that portrayed many different professions in an attempt to show young girls that they could strive for me than what they were told they could do. But that was the 1950s. This is 2023.

By no means is the world a perfect representation of equality today, but it is so vastly superior in that category than it ever has been that the theme of the film falls a little flat. Telling young girls to go after their dreams and not be beholden to any stereotypes is a positive, wonderful message and one that could’ve been portrayed so much better. But instead, the film teeters on the edge of a radical feminist position.

I’ve seen a lot of people say the film hates men. I disagree with this. I don’t think it hates men. Instead, it takes a very simplistic, black and white view of Western culture and assumes that women’s lives are overall difficult and men’s lives are overall quite easy. When in reality, life is tough. For everyone. At least 99% of us. Claiming otherwise is unjust.

However, it’s not just the political stance it takes that brings the film down. It’s how incessant it is. They are without any shame pushing a political message through the screen down your throat every 10 minutes. It’s unbearable at times. Going to the cinema or watching a film should be an enjoyable experience, not a lecture.

This film could’ve been beloved by all genders and ages. Both men and women love Margot Robbie and Ryan Gosling. This feels like an easy lay up for the filmmakers but by going the political route they end up having many jokes go over kids heads and alienate many of the people who where genuinely excited to see this film.

I give it a 6/10 because of Gosling and most of the humour. It was enjoyable overall. I think Hollywood needs to stop employing multi millionaire actors to lecture the general public on how to live. It’s embarrassing.

It’s long and I don’t know in advance how valuable it is for me. The score is 6/10 which is a hint that it can be useful for me, because I want to learn both positive and negative opinions about the film. But is the result worth the effort?

Responding to the obvious prompt (“Separate the positive and negative elements of the following Barbie movie review”), ChatGPT does the favor of separating the positive and negative elements of it:

Positive Elements:

- Ryan Gosling’s performance is described as the best part of the film, over-the-top, dumb, and hilarious.
- Every scene with Ryan Gosling had the reviewer laughing and enjoying his performance.
- Margot Robbie is praised as a great choice for Barbie, delivering a fantastic performance and hitting all the right marks.
- The theme of encouraging young girls to pursue their dreams and challenge stereotypes is acknowledged as a positive and wonderful message.

Negative Elements:

- The film is criticized for its incessant political lecturing, which is seen as a drawback.
- The strong feminist angle of the film is noted, and while the message is positive, the film is criticized for teetering on the edge of a radical feminist position.
- The reviewer disagrees with the film’s portrayal of men and women’s lives in a simplistic, black and white view of Western culture.
- The film’s excessive and constant pushing of a political message is deemed unbearable, turning the viewing experience into a lecture.
- The decision to go the political route is seen as alienating and resulting in many jokes going over kids’ heads.

Mixed Elements:

- While the reviewer enjoys the performances of Gosling and most of the humor, they give the film a 6/10 rating.
- The potential for the film to be beloved by all genders and ages is acknowledged, but the political approach is seen as a missed opportunity.
- The idea of Hollywood employing millionaire actors for societal lectures is criticized, suggesting it’s embarrassing.

Overall, the review highlights positive performances by the actors, especially Ryan Gosling and Margot Robbie, but criticizes the film’s heavy-handed political messaging and its potential to alienate and detract from the enjoyment of the viewing experience.

Now the text is much easier to comb through and I can easily find the relevant points for me (with which I may or may not agree).

Following a hint given by Karpathy, I also asked ChatGPT to structure the answer as a JSON document (“Put the positive and negative elements of the following Barbie movie review into a JSON document”). The result is pretty good, with the format being machine-readable for further processing:

{
  "Positive_Elements": {
    "Ryan_Gosling": {
      "Description": "Best part of the film, over-the-top, dumb, hilarious",
      "Scenes": "Every scene with him had the reviewer laughing and enjoying"
    },
    "Margot_Robbie": {
      "Description": "Great choice for Barbie, fantastic performance",
      "Opinion": "Hit every mark, irreplaceable in the role"
    },
    "Message": {
      "Description": "Encouraging young girls to pursue dreams and challenge stereotypes",
      "Opinion": "Positive, wonderful message"
    }
  },
  "Negative_Elements": {
    "Political_Lecturing": "Incessant and overbearing political lecturing",
    "Feminist_Angle": {
      "Description": "Strong feminist angle, expected due to Barbie's history",
      "Opinion": "Teeters on the edge of a radical feminist position"
    },
    "Simplistic_Portrayal": {
      "Description": "Simplistic view of gender roles and equality",
      "Opinion": "Disagreement, life is tough for everyone"
    },
    "Excessive_Politics": {
      "Description": "Excessive and constant pushing of a political message",
      "Opinion": "Unbearable, turns viewing into a lecture"
    },
    "Alienation": {
      "Description": "Political approach alienates viewers",
      "Opinion": "Jokes go over kids' heads, alienates excited audience"
    }
  }
}

Conclusion

If you didn’t try ChatGPT so far because of thinking that the “generative AI” genre is not relevant to you, you can try using it as an interpreter assistant.

You can even think about business models where the structuring and analysis of a large amount of text can be valuable.

Based on the example above, I offer one idea to IMDB for free: extending its website with the option to see the movie reviews in this structured format.