What the Reliquary team has invented for a minable objective is truly one of the most compelling structures i have seen for a scalable post training mechanism on Bittensor. In the same way that conjectures 66 searches math proofs, Reliquary has miners build compute fleets which search for rollouts on a target model which partition the reward landscape. You spin up a miner, download the network model and scale your inference engine + innovate on your search technique to uncover negative samples from the environments. Those samples become optimal inputs to the training process for the network model. Like how Bitcoin miners bleed energy for a hash. Reliquary miners bleed energy for a rollout. It’s a search problem at heart which is where Bittensor’s abstraction over the search for search algorithms really shines. Reliquary was created by two young engineers with no credentials and no allegiances to anything except a vision for decentralized intelligence. Bravo Rom and Grizz

Very excited crowd at Exploit. For those that missed, here is a break down of what I announced on stage.

About 97 miners competed to train the best policy for a robot navigating with no camera or map, using only a 360° LiDAR sensor. Using Bittensor’s distributed network, miners submitted policies tested on unseen environments, resulting in: > 337 submissions. > 90 hidden mazes. This is exactly how Nepher turns decentralized competition into better robotics intelligence. Watch the winning policy from Leatherback LiDAR Real Maze Phase 2 in action 👇

Novelty Search :: Bittensor Subnet 114, SOMA :: Open, Competitive Context Compression xitter.cf/i/broadcasts/1DGleVWkm…

A Harvard research team and @chutes_ai just released a public dataset covering one year of real-world LLM inference on Chutes: 6.12B requests across 9,174 models. Technical usage data from a Bittensor subnet is now open to the wider AI research community.