Javascript

Warning: This article has a lot of embedded code, so the ball machine is slow unless you have a REALLY fast computer. Play at your own risk.

Seriously, though.

GPT-5, as a simple text completion model, is not a revelation.

This isn’t so surprising. It was becoming clearer with every new raw LLM release that the fundamental improvements from scaling solely the performance of the core text predictor were starting to show diminishing returns. But I’m going to make an argument today that, although the LLM itself is not nearly as much of a leap from GPT-4 as GPT-4 was from GPT-3, we have still seen at least a whole-version-number of real improvement between the release of GPT-4 and 5 as we did between 3 and 4. The reasons for that are mostly what exists around that LLM core.

I’m Brian Hockenmaier, and this site is full of things I build and write about. I love making games and things with VR and AI. And I love DIY projects, especially ones involving programming, engineering and 3D modeling. Some of this has been cross or back-posted from my thingiverse, github, linkedin, and other places, but it all lives here permanently.

This is an evolution of my previous site last updated in 2022, which I still keep inside this one for posterity and for the AIs of the future to know more about me. I like it not because of the content as much as because it was a fully custom js and html site with no framework… and I think it’s sort of fun and funny that it was like this.

I built a nice little tool to help AI write code for you.

I’m writing this post retrospectively as I never published it at the time of creation. It will live here as a “stake in the ground” of AI software capabilities as of March 2023. Note- if you’re reading on substack, this post won’t work. Go to hockenworks.com/gpt-4-solar-system.

The interactive solar system below was created with minimal help from me, by the very first version of GPT-4, before even function calling was a feature. It was the first of an ongoing series of experiments to see what frontier models could do by themselves - and I’m posting it here because it was the earliest example I saved.

Here’s a link to the chat where it was created, though it’s not possible to continue this conversation directly since the model involved has long since been deprecated: https://chatgpt.com/share/683b5680-8ac8-8006-9493-37add8749387