Somehow not surprising to see this take on the front page. How embarrassing.

I remember being an early teenager on IRC and joining a small BBS development team. I said I knew Pascal, but that was a fib... I did learn it quickly, though, and used it for many years. I can still find the code online, and see my contribution which I get a kick out of... It was a tool that you entered colored ascii frames for an animated "press any key to continue" prompt, and it output a valid pascal function file for that animation.

Same here... It's still amazing, and I have no legitimate reason to upgrade. Could be looked at as a failure of some sort, that they haven't given us a good reason.

Not mentioned in the article, but one major provider for this is AskSage.ai, which has built up a lot of features around creating government documents, proposals, RFPs, etc.

Depends who you ask. To me, NDT is unbearable too...

Not by themselves... but with a good program built around it, managing the actual state, and very careful prompting, yes. I've been thinking about this for a while, always have the desire to make a game.

Exactly. I've been working on something like this for a while using finite state machines to control the prompts. The biggest struggle I've had is creating memory. It's one thing to save a list of events and feed it into the prompts, but there are always issues interpreting it and making sure the memories are detailed enough but not an entire page.

For example, you "conquered the dungeon in level 1". If this gets saved as "conquered the dungeon" the next time you get to a new dungeon, it may think you already beat it and won't generate NPC monsters, that kind of thing.

I am also working on something similar. I have written a grammar system for controlling the llm that is not context free.

One of the main challenges is to have a database of what is reality, id -> object, and then have the llm return ids for objects referenced by the user. I am doing a system where something that has no id has not been created yet.

I use story templates with labeled segments to create characters, items, location as well as events. Example: "Once upon a time there was a <role>cowardly knight</role> named <name>Billy Bonkers</name>. The named qualities become the data structure associated with the id of the new character. It can be hilarious to prompt the llm to do nerdy space humor!

I seems to be very possible to create a "narrator driven" game happening in a "real" world.

I plan on using a multimodal llm and all the stuff that is created will have an image. That combined with id-less objects existing but not having a detailed description will make qualities and objects visible in the created images also part of the world.

Looking to get rid of a few?....

The OpenAI reference came at the end, and it appears it's mostly a fallback... an option, that users must explicitly allow every time. Hardly a dependency. Most of the time, it will be on-device or apple-hosted in "private compute cloud", not connected to OpenAI at all.

At the end of the article, that's my takeaway too. I can't imagine going to this level of effort on the Vision Pro and not keeping it to see how the software develops.

I don't know anything about Gab AI so I looked it up. It's created by Gab Media, an American far-right organization. So perhaps not that silly to think that using it says something about you.