Kroonen AI / Studio notebook

Notes from building the stack.

Training logs, engineering postmortems, research notes, and working ideas from an independent AI product studio.

We publish the decisions, failures, and measured results behind the work—not just the polished release.

Latest entry / 006

The current field record.

Genesis 1B / Run 2

Run log Updated Apr 24, 2026 8 min read

Genesis 1B: Run 2 Complete — 80,000 Steps

Run 2 complete: 80,000 steps and roughly 42B tokens on two RTX 4090s, with a final training loss of 1.87.

Read entry

Result ledger Run complete

Steps: 80,000
Tokens: ~42B
Hardware: 2× RTX 4090
Final loss: 1.87

Notebook index / Programs

Follow the work, not the category cloud.

Entries stay attached to the program that produced them, so a run log, a failure report, and a position can be read as one technical record.

01 Program

Genesis 1B

Training runs, system decisions, failure analysis, and the ideas behind a small sovereign language model.

05 entries

006

Run log Run 2

Genesis 1B: Run 2 Complete — 80,000 Steps

Run 2 complete: 80,000 steps and roughly 42B tokens on two RTX 4090s, with a final training loss of 1.87.

Updated Apr 24, 2026 8 min read

005

Engineering note Run 2

Genesis 1B, Run 2: Nearly 3× Throughput, Same Hardware

Why Run 2 moved from 20 to 32 layers, changed its RoPE implementation, and rebuilt the training path around the same two GPUs.

Mar 24, 2026 5 min read

004

Postmortem Run 1

The Optimizer State Bug: A Silent Failure in DCP Resume

A false recovery on poisoned weights: the load path did not crash or hang—it silently ruined the model.

Mar 23, 2026 8 min read

003

Position Thesis

The Genesis Manifesto: Sovereign Intelligence for the Post-Generative Era

Data sovereignty, constitutional alignment, and the case for training language models on consumer hardware.

Updated Mar 23, 2026 10 min read

002

Postmortem Run 1

Fixing FSDP Checkpoint Deadlocks on 2× RTX 4090

How sharded DCP checkpoints and decoupled evaluation fixed training deadlocks on consumer GPUs without NVLink.

Mar 18, 2026 8 min read

02 Program

Interpretability

Experiments for finding legible structure inside model activations on hardware we can own.

01 entry

001

Research note Sparse autoencoder

Mapping the Mind of Qwen 3.5 9B

A sparse autoencoder with zero dead features and 16,384 interpretable dimensions, trained on a single RTX 4090.

Mar 15, 2026 5 min read

Open artifacts / Keep following the work

A useful note should leave a trail.

Follow the code, model releases, and product work connected to the notebook through the studio’s public repositories and model hub.

GitHub Hugging Face