Writing

Notes from an open lab.

Model releases, evaluation, infrastructure, Gaeilge AI and the case for building language technology in public.

Latest / Gaeilge

12 Jul 2026 / 9 min

The future of the Irish language in the AI era

Irish needs more than a chatbot demo. It needs licensed data, fluent-speaker evaluation, open models, durable institutions, and tools people choose to use.

Read article

02

Open source

12 Jul 2026 / 8 min

Open source is language infrastructure

For a lower-resource language, inspectable weights, documented datasets, open evaluations, and community governance are practical safeguards against digital dependence.

03

Launch

17 May 2026 / 14 min

Born-9B Preview is finally here

The launch note for Born-9B Preview: Repath at the controls, GPT-5.5 Codex managing the run, the datasets, failures, benchmarks, and the public adapter.

04

Launch

17 May 2026 / 7 min

Born Chat is open: PromptKit UI, live model lanes, and the public training loop

What shipped in Born Chat, how the Born and comparison lanes are organized, why the training notice is explicit, and what Born Chat Pro is meant to become.

05

Systems

15 May 2026 / 11 min

Why Codex GPT-5.5 Operated Born-9B

The operating model behind the run: Codex GPT-5.5 High, Repath Ray Khan at the controls, and a model release managed through evidence, caveats, and repository state.

06

Essay

14 May 2026 / 6 min

How Born-9B Learned to Breathe

The origin story of Born-9B told from the real notes: the cheap first run, the honest tie, the many teachers, and the million-token second inhale.

07

Research

14 May 2026 / 8 min

Born-9B v1: Distillation at the edge of 9 billion parameters

How we built a competitive coding-agent model in public: the data, the teachers, and the honest eval results. What worked, what did not, and every number we tracked.

08

Models

April 2026 / 8 min

A 4B that punches above 20B: reasoning distillation

LoRA on Qwen3-4B-Thinking, benchmarks vs base, the free leemerlabs/qwen3-4b-power alias, and the EU 27B+ roadmap.

09

Technical

28 Apr 2026 / 12 min

Building the Ring teacher mix: six models, one student

The data pipeline, teacher selection criteria, and quality filters behind Born-9B's training corpus. Why we chose six teachers and how their outputs were weighted.

10

Roadmap

26 Apr 2026 / 6 min

Qwen 3.6 and Granite 4.1: what is joining the EU gateway

Roadmap notes for Qwen3.6, Granite 4.1, planned EU pricing, and how that differs from today's Liquid + Gemma inference API.

11

Opinion

20 Apr 2026 / 5 min

Why evaluation-first is the only honest way to ship AI

Benchmark theater is easy. Evidence you can trust is hard. Here is how Born thinks about measurement, and why we publish evals before we publish claims.

12

Technical

12 Apr 2026 / 10 min

QLoRA on a single RTX 6000 Ada: what is actually possible

A practical account of running QLoRA fine-tuning on 48 GB VRAM. Memory budgets, gradient checkpointing, batch size tradeoffs, and measured throughput.

13

Practice

5 Apr 2026 / 7 min

Dataset provenance: why every training row needs a paper trail

We document where every row in Born-9B's dataset came from. This post explains the tooling, the YAML manifests, and why provenance matters more than row count.