Subscribe
Sign in
Home
Protein Folding
Pretraining
Fine-Tuning
Data Scraping
Language Models
About
Latest
Top
SN9: Dataset mixing delivers SOTA results
Last month, we announced that Subnet 9, Pre-training, would be enabling dataset mixing - so what were our preliminary results?
Jan 21
•
Macrocosmos
Share this post
Macrocosmos
SN9: Dataset mixing delivers SOTA results
Copy link
Facebook
Email
Notes
More
This week in the Cosmos: 2025's first Subnet status report, SN25's global job pool, and the new Gravity API
Covering the latest news at Macrocosmos, and looking ahead to Q1's upcoming releases.
Jan 17
•
Macrocosmos
Share this post
Macrocosmos
This week in the Cosmos: 2025's first Subnet status report, SN25's global job pool, and the new Gravity API
Copy link
Facebook
Email
Notes
More
December 2024
This week in the Cosmos: subnet dashboards complete, a new SDK launches, and SN9 goes to NeurIPS
Covering the latest developments at Macrocosmos.
Dec 23, 2024
•
Macrocosmos
Share this post
Macrocosmos
This week in the Cosmos: subnet dashboards complete, a new SDK launches, and SN9 goes to NeurIPS
Copy link
Facebook
Email
Notes
More
Distributed learning for decentralized LLMs: preliminary results
Breaking down our federated learning experiment.
Dec 22, 2024
•
Macrocosmos
Share this post
Macrocosmos
Distributed learning for decentralized LLMs: preliminary results
Copy link
Facebook
Email
Notes
More
Open-source, autonomous, & collaborative: understanding SN25’s approach
Looking towards subnet 25's future.
Dec 21, 2024
•
Macrocosmos
Share this post
Macrocosmos
Open-source, autonomous, & collaborative: understanding SN25’s approach
Copy link
Facebook
Email
Notes
More
How should a Subnet be scored? Crucible Labs and the art of assessment
As subnets grow in volume and diversity, the question of how to assess their performance becomes more complex - and more important.
Dec 18, 2024
•
Macrocosmos
3
Share this post
Macrocosmos
How should a Subnet be scored? Crucible Labs and the art of assessment
Copy link
Facebook
Email
Notes
More
Mixture-of-Miners: improving SN1’s performance
Experimenting with decentralized architectural changes to the LLM landscape
Dec 12, 2024
•
Macrocosmos
Share this post
Macrocosmos
Mixture-of-Miners: improving SN1’s performance
Copy link
Facebook
Email
Notes
More
SN9’s smarter dataset mixing: pushing the limits of our pre-training subnet (part 1)
Producing SOTA results with a data-centric approach.
Dec 4, 2024
•
Macrocosmos
1
Share this post
Macrocosmos
SN9’s smarter dataset mixing: pushing the limits of our pre-training subnet (part 1)
Copy link
Facebook
Email
Notes
More
November 2024
A breakdown of SN13’s dashboard: historical data, mining activity, and enhancements for Gravity
Visualizing our decentralized data scraping activity.
Nov 20, 2024
•
Macrocosmos
Share this post
Macrocosmos
A breakdown of SN13’s dashboard: historical data, mining activity, and enhancements for Gravity
Copy link
Facebook
Email
Notes
More
This week in the Cosmos: two dashboards, data mixing, and a miner arena
Covering all the recent developments happening at Macrocosmos
Nov 19, 2024
•
Macrocosmos
Share this post
Macrocosmos
This week in the Cosmos: two dashboards, data mixing, and a miner arena
Copy link
Facebook
Email
Notes
More
Introducing SN1’s dashboard: benchmarks, leaderboards, & miner stats
Providing a real-time breakdown of Subnet 1’s activity and achievements
Nov 14, 2024
•
Macrocosmos
3
Share this post
Macrocosmos
Introducing SN1’s dashboard: benchmarks, leaderboards, & miner stats
Copy link
Facebook
Email
Notes
More
SN13's Election experiment: A decisive victory for data scraping?
To what extent can social media data help predict the future? In the run up to the Presidential Election, we used SN13 to scrape posts on X for…
Nov 7, 2024
•
Macrocosmos
Share this post
Macrocosmos
SN13's Election experiment: A decisive victory for data scraping?
Copy link
Facebook
Email
Notes
More
Share
Copy link
Facebook
Email
Notes
More
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts