lingo.lol is one of the many independent Mastodon servers you can use to participate in the fediverse.
A place for linguists, philologists, and other lovers of languages.

Server stats:

55
active users

#ArtificialLife

0 posts0 participants0 posts today

If you're interested in evolution and artificial life, I can't recommend Gridworld highly enough.

It's not the prettiest game, but it's a fascinating little idler sim that evolves pixel-sized creatures using sensors, motors, and neural network controls, and lets them loose in a simple 2D world.

"Cool" doesn't quite capture the feeling you get from letting it run for a bit, and watching your world evolve from basic DNA generation to real little creatures that move, reproduce, and interact.

Did I mention it's under $1?

#gaming #artificialLife #evolution

store.steampowered.com/app/396

store.steampowered.comGridworld on SteamGridworld is an artificial life / evolution simulator in which abstract virtual creatures compete for food and struggle for survival. Conditions in this two-dimensional ecosystem are right for evolution to occur through natural selection.

Via the @ataripodcast: in a 25-minute video, Jean Michel Sellier, Research Assistant Professor at Purdue University, demonstrates the use of an #Atari800XL to train a neural network using a genetic algorithm instead of the memory-hungry technique of gradient descent.

hackaday.com/2025/02/21/geneti

I've had a soft spot for Artificial Life for a long time. During the last AI Winter in the mid 1990s, I was spurred to get back into education and onto a career in commercial software development by Stephen Levy's book "Artificial Life: The Quest for a New Creation". I loved that Artificial Life researchers borrowed well-understood mechanisms from genetics and implemented them in software to converge iteratively on solutions, in contrast to AI research, which was attempting to build models of categories which were not understood at all (and largely still aren't) - intelligence (whatever that is) and perception.

In subsequent years I wondered why I wasn't hearing any hype about Artificial Life; it turns out practitioners have been quietly getting on with solving problems using the technique. Meanwhile, yet again, AI boosters have blustered their way into the consciousness with another round of overcooked hype.

The Stephen Levy book is still worth a read, if you can find it. (IIRC Danny Hillis and the Connection Machine folks get a mention too.)

(I don't know if any of the genetic algorithm folks turned out to be supporters of eugenics, as many of the current crop of AI boosters seem to be.)

archive.org/details/artificial

en.m.wikipedia.org/wiki/AI_win

Hackaday · Genetic Algorithm Runs On Atari 800 XLFor the last few years or so, the story in the artificial intelligence that was accepted without question was that all of the big names in the field needed more compute, more resources, more energy…

We have published a new edition of the Artificial Life newsletter! Check it out here:

alife-newsletter.github.io/New

This time we feature three alife-y software projects contributed by our readers, a post-mortem of the ALIFE 2024 conference, two robots controlled by... weird stuff, and some cool art.

Please check it out, and consider contributing for the 19th edition, which we plan to release in December!

#ArtificialLife #alife

(You can also follow the newsletter by RSS, or join our mailing list)

alife-newsletter.github.ioAlife Newsletter

Artificial Life Newsletter, May edition is out!

This time we brought the review of a book about solarpunk creatures, as well as a reminder about the solarpunk conference.

We also got reviews for three fiction books that describe unique and different ways of life.

On the video side, we got a link to a video about boids and self driving cars, also links to a workshop on Universal Communication by Crosslabs.

This and more here:

alife-newsletter.github.io/New

alife-newsletter.github.ioAlife Newsletter

Hello people!

We are preparing the April edition of the ALife Newsletter, and we are looking for contributions.

Did you read anything ALife related that you want other people to know? Send us a note with your recommendation!

Want to bring some attention to your own ALife-y project? Self promotion is encouraged, send us a note too!

We plan to close the topics for this edition in two weeks.

Replied in thread

@yoginho @tyrell_turing

On that topic: I am reminded of this paper by Roth et al. 2007 on "The self-construction and-repair of a foraging organism by explicitly specified development from a single cell" direct.mit.edu/artl/article-ab (Free PDF here: direct.mit.edu/artl/article-pd)

The authors describe and implement a self-constructing virtual organism capable of Braitenberg vehicle-like properties and which can self-repair in response to damage. The properties of the damaged organism are quite interesting, in that its performance as a vehicle degrades gracefully rather than catastrophically.

MIT PressThe Self-Construction and -Repair of a Foraging Organism by Explicitly Specified Development from a Single CellAbstract. As man-made systems become more complex and autonomous, there is a growing need for novel engineering methods that offer self-construction, adaptation to the environment, and self-repair. In a step towards developing such methods, we demonstrate how a simple model multicellular organism can assemble itself by replication from a single cell and finally express a fundamental behavior: foraging. Previous studies have employed evolutionary approaches to this problem. Instead, we aim at explicit design of self-constructing and -repairing systems by hierarchical specification of elementary intracellular mechanisms via a kind of genetic code. The interplay between individual cells and the gradually increasing self-created complexity of the local structure that surrounds them causes the serial unfolding of the final functional organism. The developed structure continuously feeds back to the development process, and so the system is also capable of self-repair.

Does anyone remember a small virtual ecosystem email-based game that was around circa 1996?

The turns were every 24 hours. You played by submitting an organism with various stats and a name. It modelled population growth, grazing & predation. The next day you received an update on the world population including your organism and the organisms of other players. If your species survived you were allowed to adjust its stats by a small increment. A successful organism was a potential food source. Rules were in place so that you could only be a predator a few rungs up or down your relative position in the food chain (so emulating huge filter feeders wasn't possible).

Pretty sure it was a hobby project run from a University network, but I don't remember which. Or what it was called.

Searching for "games of life" is so full of results that I've never been able to track it down.

#GameDev
#ArtificialLife

Hello scholars and everyone!

The Artificial Life newsletter is looking for contributions to its May issue. If you want to highlight yours (or someone else's) work to the Alife community, hit us up!

We already have some pretty nice stuff for the newsletter, but new contributions are welcome. In particular, we are looking for more artistically minded content to round out the next issue!

Link to the Alife Newsletter: alife-newsletter.github.io/New

#ALIFE #artificiallife :boost_requested:

alife-newsletter.github.ioAlife Newsletter

A computer virus, written in English and Python, with a machine learning model embedded in it, authored by that machine learning model.

GPT-4 tried to escape into the internet today and it ‘almost worked’ | by Cezary Gesikowski | Mar, 2023 | Bootcamp
bootcamp.uxdesign.cc/gpt-4-tri

#GPT
#InfoSec
#ArtificialLife

BootcampGPT-4 tried to escape into the internet today and it ‘almost worked’By Cezary Gesikowski

An old project from 2001. A cellular automata where matter is conserved and the cells move around but stay connected.
github.com/timhutton/squirm

@rheophore had the same idea!

The movement of one of the colors is biased to prefer downwards steps where possible. It soon gets swallowed by the other blob. When that happens there is no escape, even though the connection rule is only local.

Hello Everyone! How about some Artificial Life news? :boost_requested:

We have just released the 9th edition of the Artificial Life Newsletter:

alife-newsletter.github.io/New

Lot's of cool stuff here, including a wearable device that mixes electronics and slime mold! Is it gross, or symbiotic?

Also, you can now follow the newsletter on RSS! Maybe a fediverse bot is next?

I worked on the newsletter together with @lana and @imytk, give them a follow too!

alife-newsletter.github.ioAlife Newsletter