Tuna Gül

AI

AI-Playground

My first neural network, written by hand in high school without libraries: neurons, layers, random weights and ReLU.

Role
Author
Period
Oct 2020
Team
Solo
Stack
Python

Code (2020) ↗

Illustration of a small 2-8-8-1 ReLU network showing only its strongest weights (solid navy for positive, dashed light navy for negative, the two strongest negatives in ochre), with an arrow to the banded decision field it produces on a toy two-spiral dataset, the class boundary drawn as a dark line; the network was trained for this cover.

What I did

In October 2020, in high school, I wrote my first neural network in plain Python to see how one works inside: a neuron with weights, a bias and ReLU, layers of neurons with random weights, and a network that passes an input through them. There is no training; I stopped after two days. The link goes to the commit before the network code was removed.

Cover: an illustration trained for this site; the 2020 code had no training loop.

Related

blueprint (bp)

blueprint (bp) Live

A command-line tool that turns AI coding agents into one team that can find and message each other, on one machine or across many.
Ridgeline of smoothed choice distributions in the 11-20 money request game: humans (ochre, front) mostly ask for 17 or 18, while LLM agents under seven persona methods (navy rows) pile up at 19 and 20.

LLM agents in economic games Research

Putting LLM agents into real economics experiments, alone or next to human players, to see what kind of society they form when they share a pot, punish and vote on their own rules.
Illustration of a light swarm of persona dots dropping answers, one column at a time, into a stacked-dot response distribution that fills up to, but never above, a plain ochre baseline curve.

simengine Research

A library that simulates how a population responds, using LLM personas, and checks every result against simple baselines.