Macrocosmos

Macrocosmos

Home
Life Science
Pretraining
Fine-Tuning
Data Scraping
Language Models
Inventive Mechanisms

Pre-Training

'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
Monsters, vampires, and X-rays: subnet 9’s Halloween deep dive
Revealing the ghoulish, trick-or-treat tactics miners are incorporating into our pre-training subnet
 • 
Macrocosmos
More oversight, better visibility: The relaunched SN9 Leaderboards
We're expanding our reporting and benchmarking for Subnet 9, bringing more granular data to the Bittensor community.
 • 
Macrocosmos
Data determinant? Why we’re updating the datasets on SN9 to improve performance
LLMs are even more dependent on their dataset than first thought. To unlock performance, higher-quality datasets are essential - which is why we're…
 • 
Macrocosmos
Subnet 9: Scaling up parameters to further Bittensor’s founding mission
There’s a growing awareness that we must democratize access to trained AI models. But as well as access, we must also democratize the training process…
 • 
Macrocosmos
© 2025 Will Squires
Privacy ∙ Terms ∙ Collection notice
Start writingGet the app
Substack is the home for great culture