Daily News 19

Tag: Stonkfly project

  • Fly Brain Connectome Powers Stock Trading and Gaming

    Fly Brain Connectome Powers Stock Trading and Gaming

    Researchers Complete Male and Female Fruit Fly Brain Connectomes for Comparative Analysis

    Scientists have successfully mapped the central nervous system (CNS) connectome for both male and female Drosophila melanogaster, enabling the first comprehensive comparative analysis of sex-specific neural wiring in the fruit fly brain. The research reveals that sexually dimorphic changes in the connectome drive specific mating behaviors, ensuring reproductive compatibility between genetically fit males and females, while the vast majority of the neural architecture remains effectively identical between sexes.

    Complete Connectome Offers New Research Avenues

    With the full connectome graph of approximately 160,000 neurons now available, researchers and developers are exploring applications beyond fundamental neuroscience. The mapped neural circuitry provides a functional blueprint of how a relatively compact biological neural network processes sensory input, generates behavior, and implements reward-based learning.

    Stonkfly Project Tests Connectome as Crypto Trader

    Developer [Nftechie] has implemented the fruit fly connectome as an autonomous cryptocurrency trading agent through the Stonkfly project. The system leverages the connectome’s native reward circuits to evaluate and execute trades. According to [Nftechie], they haven’t verified yet how good a fruit fly is at trading stocks, only that it does said stonks.

    Connectome-Driven Gameplay in DOOM and Beat Saber

    Coverage from [PC Gamer] highlights additional experimental implementations where the D. melanogaster connectome controls gameplay in DOOM and Beat Saber. In these setups, each game frame stimulates the model’s sensory neurons, while the resulting neural outputs are mapped to game controls. Dopamine-producing reward circuits are wired in to facilitate reinforcement learning, allowing the biological architecture to adapt its behavior based on in-game outcomes.

    Implications for Artificial Intelligence Research

    Although the D. melanogaster brain represents only a minute fraction of the human brain’s scale, the complete connectome offers a rare glimpse into the principles of biological intelligence. As researchers unravel how a 160,000-neuron network enables complex behaviors—navigation, learning, social interaction, and decision-making—the findings may inform the development of more efficient and adaptable artificial intelligence systems.

  • Engineer Turns Simulated Fly Brain Into Crypto Day Trader, Publishes 166,700-Neuron Model on GitHub

    Engineer Turns Simulated Fly Brain Into Crypto Day Trader, Publishes 166,700-Neuron Model on GitHub

    Coinbase Engineer Simulates Fruit Fly Brain for Crypto Day Trading with Stonkfly

    An engineer from Coinbase has created an open-source project called Stonkfly that simulates a male fruit fly brain and visual system to trade cryptocurrency in real time. The simulation connects a neural model of 166,700 neurons and 25.6 million synapses to a standard candlestick chart, allowing the virtual insect to execute buy, sell, or hold decisions.

    How the Fly Trades

    The simulated fly views a 320×180 pixel representation of historical pricing data across its left and right eyes, with an intersecting central region. Photoreceptor cells receive raw RGB pixel values rather than explicit price information. By default, the fly “thinks” and acts every 500 milliseconds, while market data refreshes every 60 seconds. Each trade can risk up to $10, with a maximum of 24 orders per day.

    Profitable trades trigger a dopamine-like reinforcement signal to 15 neurons, while losses activate two aversive neurons. Trading fees are counted as losses. The author emphasizes that no pain or emotional mechanisms are modeled. Notably, the fly cannot use leveraged positions or short selling, displaying what the project describes as far better judgement than most human traders.

    Technical Details and Caveats

    The project’s author cautions that this small experiment does not prove anything beyond the connection between input mechanisms, visual signals, and synaptic changes. He warns users against assuming those changes indicate actual trading ability, especially given a general rise in crypto prices that ‘can make any buyer look skilled’.

    Running Your Own Stonkfly

    The simulation runs on macOS or Linux, requiring 16 GB of RAM, Python 3.11, and a C++ 17 compiler. By default it operates in paper-trading mode with a virtual $100 balance using real BTC-to-USDC data. Instructions are provided for connecting a live exchange account to compare human performance against the insect’s.