memprompt VS advent-of-code-2022-in-rust

Quick Read: https://www.marktechpost.com/2022/12/18/allen-institute-for-artificial-intelligence-introduces-memprompt-a-new-method-to-fix-gpt-3-after-deployment-with-user-interaction/ Paper: https://arxiv.org/abs/2201.06009 Code: https://github.com/madaan/memprompt

It's already possible to get some of this effect with codex. The trick is to keep appending the interaction in the prompt (to maintain a memory of sorts).

For examples, you can replicate all the prompts here: https://twitter.com/yoavgo/status/1599200756631887872 with prompt + memory.

The notebook at https://github.com/madaan/memprompt/blob/main/YoavsPythonPro... shows a demo of this.

Some of these ideas were earlier discussed in our work on memory-assisted prompting [1].

[1] https://arxiv.org/pdf/2201.06009.pdf.

Code for https://arxiv.org/abs/2201.06009 found: https://github.com/madaan/memprompt

Here are my issue notes so far: https://github.com/simonw/advent-of-code-2022-in-rust/issues...

> It doesn't have any thought or understanding of its own

Of course it doesn't. Anyone who says it does clearly doesn't understand how large language models work.

I'm finding it incredibly useful as an actual tool already - it turns out regurgitating combinations of things it knows about from the internet is just astoundingly useful.

I'm having it teach me Rust for example. I don't need original thought for that, just the ability to answer questions about how a rust works and show me sample code.

https://github.com/simonw/advent-of-code-2022-in-rust/issues...