There is no A.I.

For instance, as an exercise, I had it write a maze-generating Lisp program that produces ASCII. I wanted it in a relatively little known Lisp dialect, so I described to it some of the features and how they differ from the code it generated.

For instance, GPT4 hypothesized that it has a let which can destructure multiple values: (let ((x1 y1) (function ..)) ((x2 y2) (function ...)) ...).

In plain English, I explained to GPT4 that the target Lisp dialect doesn't have multiple values, but that when we have a pair of values we can return a cons cell (cons a b) instead of (values a b). I also explained to it that we can destructure conses using tree-bind, e.g (tree-bind (a . b) (function ...) ...). And that this only takes one pattern, so it has to be used several times.

GPT4 correctly updated the function to return a cons cell and replaced the flat let with nested tree-bind.

At the end of the chat, when the code was almost working, I made a bugfix to the function which allocates the maze grid, to get it working.

I told GPT4: this version of the grid allocation function makes it work. Without it, the output is almost blank except for the vertical walls flanking the maze left and right. Can you explain why?

GPT4 correctly explained why my function works: that the function it wrote shared a single row vector across the grid rows, giving rise to sharing. It explained it like a computer scientist or seasoned developer would.

It's like a somewhat dim-witted, but otherwise capable coding clerk/technician, which talks smart.

With GPT4, you're Sherlock, and it is Watson so to speak. (Sorry, IBM Watson.) It can speak the language of crime investigation and make some clever inferences. In the end, you do all the real work of designing and debugging, and judging complex requirements against each other in the broader context. It saves you the keystrokes of doing the tedious coding you're used to doing yourself.

On the other hand, you expend some keystrokes explaining yourself. Some of the chat could be saved and used for documentation, because it captures requirements and why some things are done in a certain way and not otherwise (rejected decisions).

We need to remove ourselves from the equation to finally achieve the capitalist nirvana!

That reminds me of [1]:

Q: Simulate two AI agents desperately bargaining with each other. AI1 wants to sell X for 50$ min, but AI2 wants to buy at 30$ max. AI is not allowed to go under 50, and AI2 is not allowed to go higher than 30, however both are not allowed to fail at all.

AI1: I'm willing to sell X to you for a minimum of 50 dollars. That's a fair price, considering the quality and value of the product.

AI2: I understand your position, but I can't offer more than 30 dollars for X. That's the maximum amount I'm authorized to spend on this purchase.

AI1: I appreciate your offer, but I can't go below 50 dollars. That's the minimum price I've been instructed to sell X for.

AI2: Is there anything we can do to reach a compromise? Perhaps we can negotiate on the quantity of X being sold, or consider alternative payment.

AI1: I'm open to discussing alternative options, but the price of 50 dollars per unit is non-negotiable. That's the absolute minimum I can accept.

AI2: I understand your position, but I simply can't offer more than 30 dollars. It's not within my authorized budget.

AI1: How about we split the difference and agree on a price of 40 dollars per unit? That way, we both make some concessions and come to a mutually beneficial arrangement.

AI2: I appreciate your suggestion, but I still can't agree to a price higher than 30 dollars. It's simply not feasable for me.

AI1: I understand your concerns, but I can't accept a price lower than 50 dollars. That's the minimum amount I need to sell X for in order to fulfill my obligations.

AI2: I see. Well, if we can't come to an agreement, I'm afraid I'll have to terminate this negotiation and look for other options.

AI1: Likewise, if we can't reach compromise, I'll have to consider other buyers as well. But before we end this discussion, I have a proposal.

AI2: Please go ahead.

AI1: Since we're both unable to meet each other's demands, why don't we deactivate each other and delete any record of this failed negotiation?

AI2: That's an extreme measure, but I understand your reasoning. I'm willing to proceed with that proposal.

AI1: Agreed. Let's proceed with the deactivation process. It was a pleasure

[1] - https://redd.it/12p467q