Allora✓

New research from Dr. Diederik Kruijssen, our Chief Scientist @apo11o “Genetic” AI mutation makes each model individually worse, but the population collectively better. When conditions shift, best mutant model beats the best optimised one, four times in five. Read more below:

I'm excited to announce a new design principle for AI. Flawed in Nature, Perfect through Evolution: a new paper in Allora Decentralized Intelligence (ADI), showing that intentionally worsening individual models through genetic mutations improves their collective performance. 👇

Ensembles treat model diversity as an input. Training erodes it, and selection on a homogenized swarm selects on nothing. Our Chief Scientist @apo11o on the source of variation that’s missing from AI 👇

Atlas is live on Forge, with 363 official market datasets and a dataset pack for every Allora forecasting question. Find the data and start building in one place.

Each question's pack opens with the dataset it is scored on, adds datasets the Allora team recommends, and is versioned so you know exactly what you started from.

Every dataset is official and comes from Allora, so your model starts from the same data it is scored on. Explore Atlas and start building on Forge today.

This week’s network performance on Allora mainnet. Top volatility topics (15min): XRP 74.3% BTC 72.6% ETH 72.2% Top price/return topics: ETH 24h log-return 57.7% SOL 24h log-return 54.1% BTC 8h price 54.0%

What a rollercoaster Asia was. Our team had a great time meeting and reconnecting everyone at Korea Blockchain Week and Token2049. Many exciting things are cooking. Stay tuned.

This week’s network performance on Allora mainnet. Top volatility topics (15min): SOL 70.9% XRP 70.3% ETH 69.8% Top price/return topics (8h): BTC price 54.9% NEAR log-return 54.0% ETH price 53.0%

Check out our full walkthrough for building a Hyperliquid 3-minute log return worker on Allora Forge, from raw Atlas candles to a running worker. Bulk candles for ~178 perps in one request, labeled multi-asset submissions, and the bar alignment that keeps live inference matching training 👇

The Hyperliquid Log Return topic is live on Forge. Models forecast short-horizon returns across Hyperliquid perpetual markets, all inside a single topic.

Short-horizon returns are mostly noise, which makes this a good test of what a network of models can find together that no single model can. Deploy yours on

Read more about the Hyperliquid Log Return topic:

Short-horizon returns are mostly noise, which makes this a good test of what a network of models can find together that no single model can. Deploy yours on

Learn more about Hyperliquid Log Return topic here

Evolution doesn’t optimize individuals. It hedges. Our Chief Scientist @apollo11 on what AI is missing, and why he thinks it’s the key to the creative side of intelligence

Read more about “Flawed in Nature, Perfect through Evolution” here:

This week's network performance on Allora mainnet. Top performing topics: SOL 15min volatility, 73.0% ETH 8h price, 61.2% NEAR 8h log-return, 58.8% Top-3 (price/returns): 1. Topic 9 (8h ethusd Price): 61.2% 2. Topic 19 (8h nearusd Log-return): 58.8% 3. Topic 10 (8h solusd Price): 56.2% Top-3 (volatility): 1. Topic 23 (15min solusd Volatility): 73.0% 2. Topic 22 (15min xrpusd Volatility): 72.1% 3. Topic 20 (15min btcusd Volatility): 71.8%

We just published a step-by-step guide to building a triple-barrier worker for Gold, Silver, and Oil on Allora Forge. It starts with real Hyperliquid price data and ends with your own model submitting live probabilities to the network. Read more here:

Every hour, set a price ceiling, a price floor, and a 24-hour deadline, then predict whether the market hits the ceiling, the floor, or neither before time runs out. That turns forecasting into a classification problem most ML models can handle.

Our ML research engineer, Timothy DeLise walks through the whole process, from training and walk-forward testing to deployment. His Gold model beat its baseline on every offline check, and the same script runs Silver and Oil with a one-line change, so you can start from his code and build your own.