researchengineer.ing

researchengineer.ing

The raw, unfiltered process of becoming a research engineer. Papers. Implementations. Reasoning. Failures. Everything in between.

The gap between reading a paper and implementing it is where real understanding lives. The gap between implementing it and extending it is where research begins.

Every build here starts with an artifact, not a plan. Code, results, failure logs, derivations — in that order.

view all builds
1builds shipped
1papers implemented
3/20territories covered
3/7muscles trained

muscle coverage

Implementation Depth×1Research Taste×1Mathematical Rigor & Reasoning×1Experimental DesignSystems ThinkingCommunicationOriginal Thinking

10-month arc

Phase 1Feb–May 2026
1/8
Phase 2Jun–Aug 2026
0/6
Phase 3Sep–Dec 2026
0/8

//latest builds

Feb 19, 2026~12hP1
ArchaeologistReviewerHacker

World Models 101

A ground-up reading of Ha & Schmidhuber's World Models — the MDN-RNN memory architecture, the dream environment trick, and a minimal reimplementation in PyTorch.

#World Models#Reinforcement Learning#Generative Deep Learning
[code]
view all builds →