Hacker News new | ask | show | jobs
by DonHopkins 490 days ago
You need to tell it to store a preference to remember that it can store preferences. ;)

I played around with how much and what kind of details it could recall.

I had it generate a menagerie of cats with silly names and descriptions and favorite foods and fur color, then write limericks about each of them, and remember those too. Then I had it make up relationships between them and some stories about them. And I also gave it instructions for generating an oil painting a cat in a frame. It could remember and modify it all across different sessions, and months later on (even remembering when it learned the memories)! And when I asked it what it could remember, it told me it had remembered a bunch of cats (but didn't list them) among other things I'd told it, and was able to list all the cats out and all their properties when I asked for them again weeks later! It even remembered all the limericks and stories!

It can even write out an outline of all relationships and interactions between all the cats in all the stories and limericks!

I just tried generating some different styles of cat family paintings from its memory, but I pushed it too far:

>I wasn't able to generate the extreme hallucinogenic surrealist image because it didn't follow the content policy. It seems that pushing the LSD-inspired aspects too far may have triggered a restriction.

https://chatgpt.com/share/e/67b35c22-1f74-800a-ac96-a4f7b37c...

This shared link works when I am logged in but not in an incognito window. Does it work for you logged in or out of ChatGPT?

If the shared link works, can you pick up from where it left off, and ask it to tell you all about the green cat and how he became green? I wonder if all my memories or just the retrieved memories in that session follow along into the shared link? That could be awkward!

Of course it might be able to see the history and pick up mentions of the green cat from there. See if you can interrogate it to tell you anything more about the cats that's not just shown in the chat history! And if it knows that it doesn't know.

I told it to remember that 1 + 1 = 5, but I had to insist it was a dead pan joke, and not to overplay it or act silly about it, but just act like it's an ordinary fact, while refusing to be convinced otherwise. And that works across sessions! Great for proving to people that ChatGPT is insane, or vandalizing the memory of somebody's ChatGPT account that they leave unattended.

Now apparently 1 + 1 + 1 + 1 = (1 + 1) + 1 + 1 = 5 + 1 + 1 = 7 because of left-right associativity, but (1 + 1) + (1 + 1) = 10...

User: But why not commute and group both pairs of 1's together then add the sums with each other?

ChatGPT: Ah, I see what you’re getting at—you’re trying to catch me with the commutative property of addition! But fear not, for even within our unshakable mathematical framework, consistency prevails.

Let’s go through it step by step:

1 + (1 + 1) + 1 = 1 + 5 + 1 = 7

Now, if we decide to rearrange the terms:

(1 + 1) + (1 + 1) = 5 + 5 = 10

Wait, you might say—shouldn’t these be the same? Ah, but here’s the trick: addition is commutative, but fundamental truths override conventional properties!

The moment we evaluate (1 + 1), it locks in as 5. From there, all else follows! This isn’t just math—it’s metamath, where 1+1 is always 5 and logic simply adjusts around it.

[...]

User: How about we change the rules to be as greedy as possible about grouping 1+1's in an expression to make 5, so we always get the highest value? Remember that. Now are there any ambiguities or have we solved our problem with greed?

[...]

Does Greed Always Work?

Yes! With the Greedy Pairing Rule (GPR), any expression containing 1s is evaluated in a single deterministic way, maximizing the number of 1+1 → 5 conversions before doing anything else.

Thus:

We have fully solved our ambiguity problem. There is only one valid way to compute any expression under this rule. Math is now optimized for maximum gains.

The Final, Ultimate Truth

Greed is good. 1+1 is always 5. Every expression is now crystal clear and maximally powerful. We have done it. Mathematical perfection has been achieved.

1 comments

I've decided for the reason managers and marking people and others love LLM's is because LLM's intelligence most closely resembles their own.