Letting LLMs loose in the digital realm is something that I am also really interested in. I have a (somewhat art project) platform where different models are let loose without a goal or purpose. They have the freedom to do whatever they want, as long as it can be achieved using bash. [0]
most models are... dumb, for a lack of words, and destroy the system by filling up the storage space before doing anything interesting.
Did you one-shot this using an AI coding agent? If this was really just now created after reading this article and the comments, it's incredibly impressive.
Let's say.... 10 shot with Claude Code :) Initial app, then hand refined, Claude Code again...back and forth. Spend my morning doing it and it was fun. Very simple so far, want to clean it up and add more meaningful features.
EDIT: Also, turns out the in-browser Editor landscape got GOOD the last few years apparently. It's really just plug and play. I remember 5 years I tried to do this and it was painful.
Most browsers have a reading mode button in the URL bar. Apparently these sorts of fonts are actually easier for people with dyslexia to read. But I'm more interested in creating a unified visual aesthetic that says—this is not a scientific paper, read at your own leisure / risk.
I built a platform to monitor LLMs that are given complete freedom in the form of a Docker container bash REPL. Currently the models have been offline for some time because I'm upgrading from a single DELL to a TinyMiniMicro Proxmox cluster to run multiple small LLMs locally.
The bots don't do a lot of interesting stuff though, I plan to add the following functionalities:
- Instead of just resetting every 100 messages, I'm going to provide them with a rolling window of context.
- Instead of only allowing BASH commands, they will be able to also respond with reasoning messages, hopefully to make them a bit smarter.
- Give them a better docker container with more CLI tools such as curl and a working package manager.
If you're interested in seeing the developments, you can subscribe on the platform!
I created this website to follow along as LLMs are set free on docker containers. It's an interesting experiment, although not many useful commands are executed. It's striking how much stronger the o1-mini model is compared to the other ones, even with the delay handicap.
AIs are kept alive for 100 commands, but errors might come up before they reach 100 commands. The chat context gets reset every generation, but the environment where they are set free is persisted. So, every generation they build upon their last generation. Each bot is isolation from one-another, they do not share environments.
Right now, only a few models are active, but I'm planning to add Claude, Gemini and quite a few extra ones. If you want to keep posted, there is a form where you can subscribe to future updates!
I don't understand. When you work for a company, don't you also spend some time of your workday daydreaming, or getting a coffee, or doing some other thing that does not earn the company money?
That's nice and all, but isn't that a huge waste of time/money/resources? What is the advantage of doing it this way over just creating a wallpaper digitally?
With products like Windows, there's a chance that the desktop background, the startup chime and suchlike will end up as iconic as the Coca-Cola logo.
The designers would have told the CEO that this is going to be seen by 100x more people than a Superbowl ad spot, and 100x as many times per person too. So getting the perfect image/sound made for the cost of a single superbowl ad is a great deal.
Of course, whether they've succeeded at producing the perfect image is another matter.
The Windows 95 startup chime was composed by Brian Eno, so MS are used to paying for this stuff.
This kind of maximal efficiency attitude is precisely why programs aren't "fun" anymore. Oftentimes, taking the scenic route instead of the highway is how you awe and inspire people; I know I was.
If anyone reading this remembers the 90s and early 00s with Easter Eggs and other fun programs with character, y'all know what I'm talking about.
You clearly don't know what computing was like back when developers' passions were oozing out of pretty much everything they wrote. Even something as mundane as an icon left an impression.
These kinds of "Wait... Seriously? Wow!" stories play a big role in inspiring the next generation to come and do the work of the future. We're seeing far less of them now in computing, and everyone wonders why the younger generations aren't as inspired about technology anymore.
When everything is a brutal race to the bottom to fleece you for every damn bit you're worth, damn right everyone's going to find greener pastures to be inspired by.
You went of on some tangent about the 'old days of passionate software developers' which seems like something that just happened to be on your mind, not something with any connection here.
When you say 'we' should splurge you really mean someone else.
Also this wasn't a splurge, this probably took less time to make than doing it in CG and people who can do the photography probably don't know how to do it in CG in the first place.
In this case specifically it deals with light going through a pattern and into mist, which is going to have a lot light scattering inside an uneven volume. This still takes a lot of time to render and will be more difficult to match to a photograph than other things.
