Tiny Brains
AI
neural network competition platform
SHOW HN2026
How HN took it
5 positive, 9 neutral or asking, 1 mixed, 2 critical, out of 17 comments about the project. Thread score +0.09.
Idea: 2 for, 0 againstDocs: 0 for, 2 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Nostalgic link to the Google Ants AI Challenge.
From 2 comments
From competing with the world to building a place for the world to compete—what a full-circle moment. Love the challenge: how much strategy can a tiny neural network learn?…
Muthaalagan on HNNice. I was 72nd. Working in AI research today and still making ai for games as a hobby (tfmbot.com is an ai i’m working on for my favourite board game terraforming mars).
AnotherGoodName on HN
Fun concept with small network size focus.
From 3 comments
Great idea to focus on small, efficient neural networks.
DylanMerigaud on HNThis looks fun. How small are the networks you're aiming for?
adityamishra241 on HNPretty neat! I'm considering entering some models. How long will you be running these competitions?
willmarch on HN
Objections
Documentation was ambiguous and AI-sounding, especially weight class rules.
From 2 comments
Cool idea! It would help to delete all the text on the page, and write it without AI. For example, "model and manifest bytes together pick the class; every version also plays on…
lostdog on HN> Your class is measured, not chosen > model and manifest bytes together pick the class What? How hard is it to write something like "your weight class is determined by the total…
vova_hn2 on HN
Hard PyTorch requirement made entry difficult.
From 1 comment
OMG! Just yesterday I published my reworked GoNEAT library that implements HyperNEAT combined with phased search and backpropagation [1]. But it's kind of impossible to enter for…
cookiengineer on HN
Requests
Support more model formats beyond ONNX and a gym-style interface.
From 2 comments
OMG! Just yesterday I published my reworked GoNEAT library that implements HyperNEAT combined with phased search and backpropagation [1]. But it's kind of impossible to enter for…
cookiengineer on HNWhere do you see a hard requirement? I have added support for ONNX model upload for now and would love to extend support for other formats. How you build the model is totally…
codetiger on HN
Add more games.
From 1 comment
15yrs back I participated in "Google Ants AI Challenge 2011", an ai programming competition, hosted by the University of Waterloo, and I ranked #127 (#1 in my country). The…
codetiger on HN
Questions
How small can networks get and still play well?
From 2 comments
Interesting—how small can a neural network get and still make good strategic decisions? Curious whether these models can adapt to unfamiliar opponents.
Muthaalagan on HNThis looks fun. How small are the networks you're aiming for?
adityamishra241 on HN
How are networks evaluated, by game performance or size and speed?
From 1 comment
This looks fun. How do you evaluate the networks — is it purely based on game performance, or are there other metrics like size and inference speed too?
adityamishra241 on HN
Alternatives named
Google Ants AI Challenge
From 1 comment
15yrs back I participated in "Google Ants AI Challenge 2011", an ai programming competition, hosted by the University of Waterloo, and I ranked #127 (#1 in my country). The…
codetiger on HN
Core War
From 1 comment
See also: https://en.wikipedia.org/wiki/Core_War
lokar on HN
Screeps
From 1 comment
Also: https://screeps.com/
cheschire on HN
MIT Battlecode
From 1 comment
There is also MIT Battlecode - same idea, but for human teams https://battlecode.org/
RomanKornev on HN
MechMania
From 1 comment
Reminds me of MechMania at UIUC - exciting!
Qworg on HN
AI Wars
From 1 comment
Around 1997 there was something awfully similar to this doing the rounds, called AI Wars. IIRC it was code rather than weights, but it's a funny parallel. 30 years! God I'm old.
b800h on HN