Engineer trains simulated fruit fly to trade crypto
An engineer built an open-source program that uses a simulated male fruit fly brain—166,700 virtual neurons—to trade cryptocurrencies. The 'Stonkfly' system takes in live price charts visually, rewards profitable trades with simulated 'dopamine', and penalizes losses. It can't use risky trading methods like leverage or short-selling. The project is available on GitHub, but its creator warns not to mistake the fly's performance for real-world trading smarts.
- Simulates 166,700-neuron fruit fly brain for trading
- Trades crypto based on visual price chart input
- Profitable trades trigger simulated dopamine reward
- No leverage or short-selling allowed
- Open-source, runs on macOS or Linux
Sources covering this
In this story
More in Future Tech
Scientists publish full brain map for male fruit fly
Scientists have published the first complete map of all 166,000-plus nervous system cells in an adult male fruit fly, detailing every connection in the brain and nerve cord. The decade-long project was a collaboration between Google Research, HHMI Janelia, and other researchers, and follows the earlier complete map of a female fruit fly brain. AI powered much of the analysis, stitching together data from millions of images.
Dinosaur Coprolite Contains Exceptionally Preserved Bird Feather
Scientists found a three-dimensional feather fossil inside dinosaur droppings unearthed in Montana. The feather comes from a Cretaceous aquatic bird that didn't survive the extinction event, and may be the best-preserved example from that era. Researchers believe this rare find helps explain why only certain birds lived on to become modern species. Sometimes, major evolutionary clues turn up in fossilized poop.
Google debuts XR films at Venice Film Festival
Google’s 100 ZEROS group helped launch three interactive films using extended reality at the Venice Film Festival. The lineup includes a mixed-reality short from Andy Serkis with AI-powered dialogue, a nature experience narrated by Margot Robbie featuring a digital Charles Darwin, and a thriller teaser built with Google’s 2D-to-3D tech. All are meant for Android XR devices.
Modder runs DLSS 5 neural rendering on a second GPU
A developer has demonstrated a way to run Nvidia's DLSS 5 neural rendering on a second graphics card, letting one GPU handle the game's visuals while the other does the AI-based post-processing. This setup—involving two RTX 5060 Ti cards and a tool called MGPU Bridge—can boost performance by up to 127%, but it requires two displays and adds noticeable delay between input and what you see on screen. You can try it yourself via GitHub.