Exchange Ranking
Top Exchanges
24h Volume Ranking
Popularity Ranking
Exchange BTC Balance
Proof of Reserves
Decentralized Exchanges
Funding Rate
Funding Heatmap
Liquidation Data
Max Pain
Long/Short Ratio
Whale L/S Ratio
Binance/Okex/Huobi L/S
Bitfinex Margin L/S
ETF Tracker
Solana ETF
XRP ETF
Hong Kong ETF
Bitcoin Treasuries
Crypto Reversal
Ethereum Reserves
HyperLiquid Wallet Analysis
Hyperliquid Whale Watch
Large Transactions
On-chain Movement
Bitcoin ROI
Stablecoin Market Cap
Options Analysis
News
Articles
Economic Calendar
Features
Wallet
Contract Calculator
Security
Collections
Watchlist
Following
BTC Digital simulation based on fruit fly brains achieves small profits in Bitcoin transactions
Coinbase software engineer Alex Wormuth conducted an experiment to build a digital simulation system modeled on the fruit fly brain and achieve the modest (moderate) gains in Bitcoin transactions. Wormuth's initial investment for the project was $100. The trading system is unique because it uses a network of neural connections in fruit flies mapped in recent neuroscience research.
AI-driven fruit fly simulation enters cryptocurrency trading
This experiment, called "Stonkfly", used a highly detailed digital model of the nervous system of adult male fruit flies. The model is based on the MaleCNS v1.0 Connectome released earlier this month by an international team of scientists including Google Research. MaleCNS v1.0 is a comprehensive blueprint for the central nervous system of fruit flies.
Although Stonkfly uses advanced neuroscience principles, there are no real insects at the trading table. Instead, the system operates by receiving real-time BTC-USDC market data from Coinbase. The data is converted into RGB images that simulate the way insects perceive visual information. The processed images are sent to thousands of simulated sensory neurons to recreate real insect brain activity.
Just one day after the experiment began, the Stonkfly transaction generated a profit of $1. However, Wormuth points out that this small gain is likely to be the result of chance rather than continuous learning. Because the system's trading decisions closely depend on market fluctuations and the randomness of its simulated neural responses.
Stonkfly uses a complete adult fruit fly connection set to map real-time Bitcoin price data into simulated sensory input. Depending on the profit or loss, the trading results trigger specific dopamine neurons or average-responsive neurons, respectively.
Miniature Dictionary: Connectome -A comprehensive map of neural connections in the nervous system of organisms, commonly used in neuroscience to computationally model and simulate brain activity.
Stonkfly simulates the brain's trading mechanism
Stonkfly's mechanism involves activating 15 simulated PAM11 dopamine neurons when a portfolio records profits, which mimics reward signaling in living insects. In contrast, if a loss occurs, it triggers two PPL101 neurons associated with fruit fly aversion responses.
Despite these complex mechanisms, current systems have not yet demonstrated reliable learning capabilities or autonomous decision-making capabilities. The initial $1 profit may simply reflect natural price fluctuations and random trading, rather than true adaptability or strategy development.
Background and Future Applications
The release of the complete adult male fruit fly connection group marks a major advance in neuroscience. The map contains 166,700 neurons and defines complex wiring that runs through the insect's brain, optic lobes and ventral nerve cords. Such connected group projects enable high-precision simulations for scientific and experimental purposes.
Wormuth, who works at leading U.S. cryptocurrency exchange Coinbase, has previously been involved in work on the MaleCNS model, most notably linking it to the classic video game Doom in a project called DOOMFLY. Other developers have made similar integrations, connecting fruit fly simulations with games such as Beat Saber, Super Mario 64, Minecraft and Pong.
Although the simulation model depicts complex wiring structures, many key elements of the biological brain are still beyond the reach of current technology. Functions such as chemical neurotransmitters, gene expression, and broader regulatory processes are not included in these digital connecset models and cannot currently be fully reproduced outside of real organisms.
