Technical research posts covering MoE architectures, distributed training, and AI alignment.
View All TagsPhase 1 of BlockZero is a training platform: customers bring domain data, miners train expert modules, validators evaluate quality, the expert library grows. Phase 2 is what the library enables: a marketplace where validated domain experts are discoverable, testable, and licensable.
Before building BlockZero, we surveyed the literature on distributed Mixture-of-Experts training. This is a practical synthesis of what we found — what methods exist, what problems they solve, where they fall short, and what gap BlockZero fills.
Every decentralized compute network faces the same incentive problem: how do you reward workers for doing actual work, rather than for appearing to do work? BlockZero's Proof-of-Loss mechanism is our answer — and it's the property that makes the network's quality guarantees credible.
Catastrophic forgetting is the central unsolved problem of continual learning. You train a model to be better at task B, and it forgets how to do task A. The more you specialize, the more you destroy. BlockZero's MoE architecture makes this tradeoff avoidable — by construction.
Most AI customization is one-off work. A consulting firm spends six months fine-tuning a model for a client, and when the engagement ends, all that accumulated knowledge walks out the door. The next client starts from scratch. There is no compounding.
BlockZero is built around a fundamentally different model: every training job produces a reusable expert module that compounds in value with every subsequent use.
This post introduces TEFT (Targeted Expert Fine-Tuning) — the protocol at the core of BlockZero — and explains how it achieves communication-efficient, quality-gated distributed MoE fine-tuning over a permissionless network. This is the research paper translated into blog form.