---
title: "Adam Yang (@adamygn) | Hashnode"
description: "Adam Yang (@adamygn) writes on Hashnode. Read their latest articles and follow their work."
url: "https://hashnode.com/@adamygn"
---

@adamygn

# Adam Yang

@adamygn · Joined October 2025

### [Turning Latency into Throughput: Speculative Decoding for the Decentralized Inference](https://gradient.network/blog/turning-latency-into-throughput-speculative-decoding-for-the-decentralized-inference?utm_source=hashnode&utm_medium=feed)

https://arxiv.org/abs/2511.11733 The Latency Wall In centralized inference, speed is mostly a function of compute. You optimize by saturating HBM bandwidth, fusing kernels, and keeping GPUs close to their roofline. In decentralized inference, where...

6 min read · [gradient.network](https://gradient.network/blog/turning-latency-into-throughput-speculative-decoding-for-the-decentralized-inference?utm_source=hashnode&utm_medium=feed)

[Nov 24, 2025](https://hashnode.com/posts/turning-latency-into-throughput-speculative-decoding-for-the-decentralized-inference/69244a5d5f55d14f0512a90e)

### [Lattica: A Universal Communication Substrate for Open Intelligence](https://gradient.network/blog/lattica-a-universal-communication-substrate-for-open-intelligence?utm_source=hashnode&utm_medium=feed)

https://arxiv.org/abs/2510.00183 Lattica is a communication tool that solves internet barriers like firewalls. It lets scattered computers securely connect and work together to run powerful AI, creating a global, open network. Introduction: The Mi...

4 min read · [gradient.network](https://gradient.network/blog/lattica-a-universal-communication-substrate-for-open-intelligence?utm_source=hashnode&utm_medium=feed)

[Oct 1, 2025](https://hashnode.com/posts/lattica-a-universal-communication-substrate-for-open-intelligence/6900635c16fa1ba3be0140b8)

### [Massgen: When Multiple LLMs Think Together](https://gradient.network/blog/massgen-when-multiple-llms-think-together?utm_source=hashnode&utm_medium=feed)

https://arxiv.org/abs/2509.23537 Massgen makes different AIs work together as a team, debating and voting on answers. This collaborative approach overcomes individual weaknesses, achieving smarter results than any single AI could alone Introductio...

4 min read · [gradient.network](https://gradient.network/blog/massgen-when-multiple-llms-think-together?utm_source=hashnode&utm_medium=feed)

[Sep 30, 2025](https://hashnode.com/posts/massgen-when-multiple-llms-think-together/690076905a897aca6fba63f7)

### [Parallax: Your Sovereign AI OS](https://gradient.network/blog/parallax-your-sovereign-ai-os?utm_source=hashnode&utm_medium=feed)

https://arxiv.org/abs/2509.26182 Why this matters First things first: we want your personal AI agents to be sovereign. It should not upload everything it sees to a giant centralized cloud. What it learns about you should live as a portable local me...

9 min read · [gradient.network](https://gradient.network/blog/parallax-your-sovereign-ai-os?utm_source=hashnode&utm_medium=feed)

[Sep 30, 2025](https://hashnode.com/posts/parallax-your-sovereign-ai-os/6901b2091d0594b853b3d7de)

### [Veri: The Trust Layer for Distributed Inference](https://gradient.network/blog/verillm-distributed-serving-with-trust?utm_source=hashnode&utm_medium=feed)

https://arxiv.org/abs/2509.24257 VeriLLM is a verification protocol for large language models that run across a decentralized network of volunteer GPUs. Its goal is simple and strict: when you ask a model to run on untrusted hardware, the answer yo...

7 min read · [gradient.network](https://gradient.network/blog/verillm-distributed-serving-with-trust?utm_source=hashnode&utm_medium=feed)

[Sep 28, 2025](https://hashnode.com/posts/verillm-distributed-serving-with-trust/69006bdc593c6e75e048ba77)
