eyvindn

Joined 8 years ago

Karma
439
Submissions
50
Member since
May 2
http://eyvind.me/ eyvind.niklasson (at) gmail.com

Machine Learning, currently focusing on self organising systems.

View on Hacker News

Recent submissions

Comment · 3 months ago
the unity/minecraft level of abstraction is a common one in AFIFE, and too often ends up being Spore - looking and behaving in very interesting ways, but remaining just that. those approaches are on the wrong side of the performance vs evolvability curve - scale is a necessary ingredient and running things at a physics sim level is just too taxing.

it is of course entirely possible we are on the flip side and too low-level - this is something we're trying to find out.

Comment · 3 months ago
yes! very soon!
Comment · 3 months ago
this is my personal take;

I agree, for the same reasons you mentioned, resource constraints will need to be baked in (they are already, to some extent, if you consider the constrained resource to be z80-CPU-seconds the program has access to). something more akin to energy in our real world, which can be manipulated, aggregated, shared, pooled, stolen, etc feels more natural, however.

imo meaningful intelligence could conceivably developed in a soup (even in-silico), unclear on what timeline, but grounding it with human and/or real-world data is necessary to make it useful to us (bio-compatible, if you will?)

Comment · 3 months ago
there are many bottlenecks in the substrate - memory limits being one of them. other things like the A-B concatenation inherited from the bff paper also severely limit the possible dynamics. understanding and avoiding these bottlenecks are some of our next steps!
Comment · 3 months ago
as other folks have replied, Z80 is more expressive and yields more interesting replicators faster. however the question of how complex to make the "base layer", if you will, remains open. we expect it to also be an ease of auto-evolution vs. performance tradeoff.

second question is a good question :)

Comment · 3 months ago
authors here - happy to answer any questions! we’re excited for this line of work and see this as the first step on a longer journey.
Comment · 3 months ago
^ yes. this is what we hope.
Comment · 1 year ago
:)
Comment · 1 year ago
colab with all code will be available next week, will add link from the article.
Comment · 1 year ago
thanks for catching this, the figure for the target was inverted when exporting for publication, corrected now.
Comment · 1 year ago
could you link the drone swarm command article?

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton