Lab Notebook

How Discovery Engine Is Made

Discovery Engine is written by a human author working in deep collaboration with AI systems — Claude (Anthropic) as primary collaborator, with Gemini (Google) and ChatGPT (OpenAI) in supporting roles. This is not a disclaimer. It is a methodological commitment, and it is on-theme: a blog asking whether machines can discover should not pretend to be written by a human alone.

For each post, we publish a Lab Notebook entry: source materials, iteration history, AI inputs and reviews, editorial decisions, and what we learned along the way about working with multiple AI systems. The Lab Notebook is, in a small but real way, an artifact of the human–machine collaboration that this blog is about.

Entries

Post #1 — Can Machines Discover?
Read the post →
Read the Lab Notebook entry →
Published: 27 May 2026

Post #2 — Human Cognitive and Behavioral Limitations in Scientific Discovery
Read the post →
Read the Lab Notebook entry →
Published: 15 June 2026

Post #3 — Connecting Distant Dots
Read the post →
Read the Lab Notebook entry →

Published: 15 June 2026

Machine Traces of Discovery Paths #1 — Lab Notebook
The evidence behind the Deep Dive essay “Machine Traces of Discovery Paths #1 — The Path to iPS Discovery.” Four technical documents: the trace reconstruction, the methods-and-findings report, and — for the NAT1 (2000) hinge experiment — the structured protocol extraction and the tagged bench reconstruction. Each document is self-contained
The Discovery EngineHiroaki Kitano

Seed article: EMBO Journal (2000), used as the sole seed article for protocol reconstruction for NAT-1 function identification

Machine Traces of Discovery Paths #2 - The Path to iPS Discovery, A Comprehensive Analysis and Reconstruction
Machine Traces of Discovery Paths — Autonomous reconstructions of how landmark discoveries were reached, traced by AI from the primary literature. Disclaimer — Discovery Trace Series. The Discovery Trace series is an experimental series of articles attempting the semi- or fully-automatic reconstruction of the paths to major discoveries. Multiple AI tools
The Discovery EngineHiroaki Kitano

Seed article: A set of article by Shinya Yamanaka leading to the discovery of iPS Cell.

Machine Traces of Discovery Paths #3 — Lab Notebook
Evidence for the Deep Dive essay Machine Traces of Discovery Paths #3 — The Path to CRISPR-Cas9 (Jennifer Doudna), A Comprehensive Analysis and Reconstruction. This Lab Notebook is the verifiable source record behind the #3 Deep Dive. It reconstructs, from the primary literature, the path that carried Jennifer Doudna from
The Discovery EngineHiroaki Kitano
Machine Traces of Discovery Path #4 - Lab Notebook
Disclaimer — Discovery Trace Series. The Discovery Trace series is an experimental series of articles attempting the semi- or fully-automatic reconstruction of the paths to major discoveries. Multiple AI tools have been deployed to reconstruct each “Discovery Path.” To evaluate the progress of the technology, an initial set of articles
The Discovery EngineHiroaki Kitano

The practice of public process documentation will accumulate over time. Each post in Discovery Engine has, or will have, a corresponding Lab Notebook entry. The notebooks are reference material — they are not optimized for readability, only for honesty.