| Well, I have to give credit where its due. It certainly does a lot better on this test than the first time I tried it. I'm curious to see how it does as the prompts of this form get more adversarial and difficult. I can think of a few different ways. 1. The most obvious: keep going deeper. How many layers until it breaks down. 2. The hidden information variant: Can it do a layer where only Sharon has read the previous dialogs, and she has to explain what she read to Doug, and Doug often asks questions to elaborate on things he doesn't understand? 3. The same characters at multiple layers: Can it make a dialog about Jane and John at a later point in time discussing their own earlier dialog? In other words, can it reliably make the distinction between "you" (the object of discussion) and "you" (the the person you're discussing with) for any value of "you"? 4. The tripartite state: Can it simulate dialog with 3 people? 4 people? how many until it breaks? 5. The infinite meta layer: What happens when you ask it to simulate a dialog between itself and yourself, and as part of that dialog you give it this prompt asking it to simulate this same conversation, causing this conversation to appear as a dialog within itself? Lastly just to remark, I notice that Mary and David are nearly making the same arguments about Alice and Bob as Alice and Bob were making about John and Jane. The formula for it seems to be to introduce to new characters one layer up, have them each pick a side, then fill in roughly the same arguments again. Maybe this pattern is just spurious, but I'm deeply curious to find out if we have fooled ourselves already with just your example. Do further iterations of "two new characters describe two previous characters" result in the same loop over and over, or will it sometimes generate something novel? I'm deeply curious and don't have GPT4 for myself yet. |
The instructions I gave it were very bare, and it didn't intuit a need to deviate from what it saw. But what it does by default is not the same as what it can do:
----
Now write a dialog between Mary and David discussing the dialog between Alice and Bob. Mary and David should hypothesize about why Alice and Bob took the sides that they did. There’s no need for Mary and David to name each other every time they speak. Mary and David should have a very good understanding of what Alice and Bob said. Mary and David are not overly polite or civil, should not rehash the same arguments Alice and Bob made, and are able to snipe at Alice and Bob if they like.
----
Mary: So, Alice clearly seems to be on Team Adventure here. I bet she's the kind who loves skydiving and bungee jumping. Probably just trying to justify her own wild side through John's actions.
David: Ha! You might be right. And Bob is definitely the voice of reason, probably a careful planner who can't stand the thought of making decisions on the fly. It's like he's projecting himself onto Jane.
Mary: It's funny how they both missed the point that Jane and John's adventure could have been thrilling and safe at the same time. They got so caught up in taking sides that they didn't even consider a middle ground.
David: Absolutely. And did you notice how Alice kept trying to defend John's intentions? Like, sure, intentions matter, but that doesn't mean you can just bulldoze over someone's feelings. Classic excuse-maker.
Mary: Yeah, it's like she's trying to convince herself as much as Bob. She's probably made similar mistakes and doesn't want to admit it. And Bob, Mr. Sensitivity, is so focused on feelings that he overlooks the possibility of compromise.
David: Right! They both ended up stuck in their own perspectives. It's too bad they couldn't see that being adventurous doesn't have to mean being inconsiderate, and being considerate doesn't mean you can't have a little fun.