What is mattwood.fyi?

A live, structured feed of riffs and links from Matt Wood, Chief AI & Technology Officer at AWS — readable by people and queryable by agents as a typed knowledge graph.

Is there an API and is it free?

Yes. A public, read-only query API is available with no authentication and no API keys. See https://mattwood.fyi/openapi.json and https://mattwood.fyi/docs.

How should an AI agent use this site?

Fetch https://mattwood.fyi/feed.json for the full structured feed, or query the API for keyword/semantic search and the connection graph. See https://mattwood.fyi/agents/ for when-to-use guidance.

Autonomous AI agents discover reverse transcriptases with tandem repeat arrays

Connections

Supports

GDM Science Skills: Agentic Scientific Workflows Both demonstrate autonomous AI agents conducting scientific discovery workflows — GDM Science Skills focuses on agentic scientific workflows broadly, while this item shows a specific case of Claude autonomously identifying novel biological sequences (ART family reverse transcriptases) through pattern recognition
The Millennium Problems for Biology The Millennium Problems for Biology frames grand open challenges in biology; autonomous AI discovering novel reverse transcriptase families exemplifies the kind of AI-accelerated biological discovery that could address such frontier problems
Declarative Attention: Models Controlling Their Own Attention Declarative Attention explores models controlling their own attention mechanisms; the attribution of Claude's ART family discovery to 'specific Mythos 5 internal signals that respond to repeated patterns' is a real-world behavioral correlate of models self-directing attention toward salient sequence features

Related to

SWE-bench Science: Coding Agents in Scientific Software Engineering SWE-bench Science evaluates coding agents on scientific software tasks; this item similarly probes agentic capability in science but reveals that specific internal model signals (Mythos 5) drive discovery behavior, adding mechanistic insight beyond benchmark performance
AlphaGenome Atlas Both involve AI systems analyzing genomic/biological sequences at scale — AlphaGenome Atlas and this ART family discovery both represent AI-driven biological sequence analysis, though the latter highlights emergent agent behavior rather than supervised genome annotation

Develops into

AI in Science AI in Science broadly covers AI's role in research; this item is a concrete instantiation showing how AI agents move beyond assistance into autonomous discovery — identifying the ART family through internal signal responses to sequence patterns represents a qualitative advance described by that broader framing

Type:	link
First published:	Thursday, 24 September 2026 at 07:49 UTC
Location:	https://www-cdn.anthropic.com/22573675ada52a8ca8a97a1a4b4326b2f208a071.pdf
URL:	https://mattwood.fyi/i/0c4b7354

I'm Matt Wood, and this is For Your Information. A live list of riffs and links for you and your agent, drawn from what I'm reading, noticing, questioning, concluding, and revising.

Connections