Wren is super neat. I've written a few small games for TIC-80 using it. It's a really fun language to write.

I think Google has proven with their recent actions concerning android that they really can't be trusted with big, critical open source projects.

> trusted with big, critical open source projects.

You talk as if the community has appointed Google to take care of these projects. Google is spending $$$ writing code and open sourcing it. Not the other way around.

And as with anything open source, if you dont like the direction of open source code - fork it.

If I have an open source project, you dont say 'bitpush cant be trusted with the project'.

Where is the source code for AOSP 16 QPR1?

Where are the security patches of the past couple of months?

What is QPR?

I tried this. It sounds good on paper but the LLM will just "forget" to use it's tools. Either it will decline to query the database and just make stuff up, or it will decline to update the database when it should. The further along the game play gets the more out of sync the game word gets from the external state. I'm sure there is a clever solution but I never found it.

you're making the mistake to assume that leaving the structure of the communication and game play to the LLM is the only option. the LLM just is a tool serving a specific purpose in the game play. the LLM cannot forget to query if the query/state-management task is simply an imperative step in a loop. it's not left to the LLM to remember it.

Neat, it seems to me like Lua is a great language for text adventures.

In this case I chose Lua not for its suitability to the problem but because the computer my child has is a NetBSD machine with few things besides Lua installed on it.

Cool, so the computer is fairly locked out of social media etc, which is neat

Not even connected to the internet! Whicih is why I picked a BSD -- fairly complete on its own. We'll see how long I can keep it up. I hope to make "connecting to the internet" a temporary thing done for a specific purpose and then one disconnects.

I love text adventures. Collosal Cave Adventure and Zork are some of the coolest programs I've ever seen.

I've always wanted to try writing one and this article might have just inspired me to finally do that.

I recommend learning something like Inform 6, Inform 7, or TADS 3 if you want to make a text adventure.

It is as they say: if you want to make a game engine, make a game engine. But if you want to make a game, use an existing engine.

If you like the Zork "engine", learn Inform 7. If you like the Colossal Cave "engine" better, you might like to look at https://github.com/Quuxplusone/Advent/blob/master/ODWY0350/a... — it's very easy to remodel with your own rooms, items, verbs, and so on. (So is the original Fortran, but then you have to be able to compile Fortran...)

This is a neat idea and I wish it worked. I've spend hours and hours trying to get LLMs to be a "dungeon master" for text adventures. I've written a good amount custom code trying to facilitate this. Trying to force the LLM to keep it's story straight.

I'm pretty convinced that the current generation of LLMs is nowhere close to being capable of this. No matter how many context hacks you throw at it.

It inevitably derails and ruins the immersion.

Best of luck on this. If you can pull it off it would be really cool I think.

Currently working on an idea like this, but its a history simulator for educational use - I find that LLMs respond rather well to being grounded in a specific time/setting in real world history, as opposed to being told to roleplay a fictional setting. The latent space of any fictional world is close enough to other fictional worlds that they will rapidly slide off into other similar-sounding settings. Whereas if you return them to a super-specific historical context each go-around ("The time is now 3:13 pm. It is August 3, 1348. You are currently simulating the functioning of a small vineyard in Normandy. The farmer, [NPC name], is looking for helpers in the fields") they will be able to pull from a pretty solid baseline of background knowledge and do a decent job with it.

Some fun things I've been experimenting with is 1) injecting primary sources from a given time and place into the LLMs contex to further ground it in "reality" and 2) asking the LLM to try to simulate the actual historical language of the era - i.e. a toggle button to switch to medieval French. Gemini flash lite, the only economical model for this sort of thing, is not great at this yet but in a year or so I think it will be a fascinating history and language learning tool.

Have been meaning to write this project up for HN but if anyone wants to try a very early version of it, it's here - you can modify the url to pick a specific year and region or just do the base url for a fully random spawn, i.e. here is Europe in 1348: https://historysimulator.vercel.app/1348/europe

I think a big part of it is not so much that they aren't capable of being a dungeon master, but they are constitutionally unfit due to their agreeability.

The biggest improvement there is to treat the game engine as the "user", and the player (and their input) is merely one among many things the game engine is managing. But then you also need a game engine that manages lots of the state programmatically, with formal transitions of that state. The LLM can manage the state transitions, but the actual state needs to be more formal.

I found this article really interesting. This is pretty much exactly how I feel about LLM programming.

I really enjoy programming and like the author said, it's my hobby.

On some level I kind of resent the fact that I don't really get to do my hobby for work any more. It's something fundamentally different now.

For what it's worth, I wrote a very bare bones RSS reader in an afternoon. It really just renders a set of RSS feeds into HTML and nothing else.

But it was fun to and educational to build and could pretty easily be extended to add more features.

I would recommend just going for it if you are interested in writing one. It's not as hard as it sounds.

I've always wanted to make an app like this. I think you could do a lot with procedural generation and some clever DSP.

It really does seem like the idea of DRM free games and Linux goes hand in hand. I would be really interested to hear about why they don't currently offer Linux support for their launcher.

I'm in the same boat here. I would be more than willing to rebuy some games on GOG if they supported Linux.

The idea of running old Windows games definitely doesn't go hand in hand with Linux. And I think GoG simply has way more Windows experience, lots of work to do, and little realistic chance of tapping some huge market if they spent all the time you need to support 2-3 major Linux distros - especially when you need to offer things like Multi-player support as well on those, plus maybe game recording and whatever else the overlay offers (GoG Galaxy is not just a storefront).

Why not? My experience has been that old games run easier and better on Linux than Windows thanks to Wine and Microsoft's stupidity

Does it work with wine/proton? anecdotal but even in apps/games where they make a linux port the wine/proton version sometimes works better.

I have Linux GOG games which refuse to run for one reason or another. Some outdated library, compiler, whatever that is not on a modern distribution.

If you want easiest future proofing, you have to use the windows release.