Macrocosmos

Macrocosmos

Home
Bittensor's best
Life Science
Pretraining
Data Scraping
Language Models
Inventive Mechanisms

Pre-Training

The Economics of Liquid Training
In this piece, we lay out the shape of the market today, how different compute workloads create value, how the capital model for GPUs works, and how…
 • Macrocosmos
The Case for Liquid Training
Thesis Compute is the limiting reagent of modern intelligence.
 • Macrocosmos
Orion-100B: Distributed pretraining arrives at hundred-billion-parameter scale
Author: Dr. Steffen Cruz
 • Steffen Cruz
The IOTA Simulator, on Apex
New SN1 Competitions Designed to Accelerate Distributed Training
 • Macrocosmos and Kai Morris
Welcome to Train at Home
SN9’s Train at Home is available to all. Here’s what you need to know.
 • Macrocosmos
'You get torn apart - but that's how you evolve' Brian McCrindle on proteins, pretraining, and pushin' to prod
OTF, Mainframe, IOTA: Brian has contributed to some of Bittensor's best systems. So we sat him down to ask about his lessons along the way.
 • Macrocosmos and Brian McCrindle
Why IOTA is different: Comparing Pretraining, Federated Learning, and Swarm
Subnet 9 has relaunched with a brand new decentralized pretraining setup, but what exactly sets it apart from others on Bittensor?
 • Macrocosmos
IOTA: Bittensor's biggest pretraining breakthrough is here
Subnet 9 is now the home to the world's first ever model parallel and data parallel incentivized trustless pretraining protocol - proving Bittensor’s…
 • Macrocosmos
Rebalanced, refined, and SOTA: Our latest dataset mixing results in SN9 (part 3)
Increasing our dataset mixes has provided even stronger outcomes - with our top two models surpassing DeepSeek-V2-Lite, Google’s Gemma 7B, and Mistral…
 • Macrocosmos
SN9: Dataset mixing delivers SOTA results (part 2)
Last month, we announced that Subnet 9, Pre-training, would be enabling dataset mixing - so what were our preliminary results?
 • Macrocosmos
Distributed learning for decentralized LLMs: preliminary results
Breaking down our federated learning experiment.
 • Macrocosmos
SN9’s smarter dataset mixing: pushing the limits of our pre-training subnet (part 1)
Producing SOTA results with a data-centric approach.
 • Macrocosmos
© 2026 Will Squires · Privacy ∙ Terms ∙ Collection notice
Start your SubstackGet the app
Substack is the home for great culture