Skip to content
Discuss your first workflow

Notes from the inside.

Ideas, evidence and working examples from building the Twin. Read the thinking. Explore how it works.

Featured / Research

I wanted more than 200 tokens per second from Qwen3.8-27B on one RTX PRO 6000. Getting there meant going below the serving framework.

George Pullen · 8 min read

Read the article
NVFP4, DFlash2 and what it actually takes to make an open model run properly on hardware you control.

All the field notes.

29 articles

Twin / Field note

How a Digital Twin Is the Key to Running a Portfolio of Fast-Growing Companies

How I run four fast-growing companies from one seat, what a digital twin actually is, and why playbooks - not the model - turned out to be the unlock.

11 min readHenry Allen
Research / Field note

Three Cents of Probing Says Jev Is a Small Qwen in a Very Good Suit

I sent Jev about 120 requests and roughly $0.03 of API spend. The token counts, the 32,768 context limit and the punctuation behaviour say pretrained Qwen-class LLM, customised tokenizer and parallel scoring heads. No new science, but genuinely good engineering.

5 min readGeorge Pullen
Twin / Field note

What Should a Twin Learn From a Mistake?

An overdue invoice exposes a missing question. Could a Twin learn to ask it next time? A proposal for context that improves through evaluated, reversible changes.

11 min readArchie Norman
Research / Field note

I Built a Custom Blackwell Kernel for Qwen3.8-27B

I wanted more than 200 tokens per second from Qwen3.8-27B on one RTX PRO 6000. Getting there meant going below the serving framework.

8 min readGeorge Pullen
Research / Field note

China Is Winning the Post-Transformer Race

I am bullish on Moonshot, Alibaba and Z.ai because they are releasing architectural progress that the rest of us can actually build on.

4 min readGeorge Pullen
Research / Field note

The Token Is a Narrow Feedback Channel

A close reading of the full-bandwidth transformer: what latent feedback changes, what the 1B-parameter experiments establish, and why hidden computation cannot replace governed evidence.

9 min readGeorge Pullen
Research / Field note

RFQ1: Building a Relation-First Query Language for Project Venus

How RFQ1 represents relational queries, what its ten clauses mean, and how grammar-guided token masking can restrict a model to the language by construction.

3 min readGeorge Pullen
Research / Field note

Adapting Qwen3-VL Representations for Open-Set Continual Visual Learning

A four-stage investigation into whether Qwen's internal visual representations could support few-shot, open-set continual learning.

8 min readGeorge Pullen
Twin / Field note

You Are Not the Front Door

Why the user's chosen agent may become the primary entry point to software, and why every company will need a governed Twin between those agents and its systems.

11 min readArchie Norman
Twin / Field note

Your AI Doesn't Need More Context. It Needs Approved Meaning.

When sales, finance and delivery use the same words differently, retrieval alone cannot settle the report. Make the definition explicit, versioned and reusable.

5 min readArchie Norman
Twin / Interactive essay

Five Gates Between a Guess and a Governed Answer

Follow a recurring-revenue definition through five distinct controls, and see why evidence from one cannot stand in for another.

5 min readArchie Norman
Twin / Interactive essay

One Twin, Many Interfaces

A practical map of how enabled interfaces reach the Twin, what stays consistent across them, and why a connection never grants itself wider access.

4 min readArchie Norman
Stay curious

More notes, as we build.

Get the research briefing, or follow new articles in your own reader.

Two ways to start

Start with the question your team keeps chasing.

Your first workflow

Show us a recurring report, an awkward handover or a decision that takes too long to prepare. We’ll explore where your Twin could help and agree a useful starting point.

Partnership

Bring the Twin to your clients. Talk to Mercury Labs, the team behind your Twin, about delivery and partnership options.