vicgalle_
Joined 3 years ago
Karma
185
Submissions
17
Member since
Dec 2
https://github.com/vicgalle
View on Hacker NewsRecent submissions
Comment · 2 months ago
The curve: https://elliptic-rank.icarm.cloud/curve/302
Comment · 3 months ago
A small update here: another replication using a different CPU, the 6502. In this case, replicators emerge 100 times less frequently than in Z80, due to a lacking LDIR-like instruction
Comment · 3 months ago
See replies at this other comment https://news.ycombinator.com/item?id=48963513
Comment · 3 months ago
> Do you have any idea why the authors chose Z80 as the program language?
In that previous paper you cite (by the same group) they tested several substrates for spontaneous replication (BFF, Forth, SUBLEQ, and emulated real CPUs. Z80 and 8080 CPU exps confirmed the rise of self-replicators, with the Z80 notably exhibiting multiple waves of increasingly capable self-replicators.
And the instruction set seems quite appropriate for the experiment: Z80 has native block-copying instructions, while it doesn't have MUL, so the task of evaluating polynomials is somewhat more challenging
Comment · 3 months ago
Thanks for posting this, indeed that group at google has produced some interesting research in this space.
That paper was also discussed here back in the day: https://news.ycombinator.com/item?id=40820022
Comment · 3 months ago
An independent reproduction of the main result: https://github.com/vicgalle/coevolution-soup
Comment · 4 months ago
I enjoy creating new benchmarks for LLMs. Lately, combining scientific computing tasks (n-body sim, Monte Carlo, etc) with Apple Metal GPU kernels (evolved through LLMs) led to a curious benchmark I believe: https://github.com/vicgalle/metal-sci-kernels
Comment · 2 years ago
> https://twitter.com/minimaxir/status/1749893683137454194
Not very promising, though.