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.

Introducing Ember-1 — mattwood.fyi

Connections

Supports

Unreal Agent: Cost-Efficient AI Agent Harness Ember-1's token efficiency directly enables cost-efficient agent harnesses — lower token consumption per task compounds savings when deployed in multi-step agentic workflows
Strands Harness: Frontier Performance with 28% Lower Token Cost Both items highlight efficiency gains through token reduction — Strands Harness achieves 28% lower token cost while Ember-1 achieves 40% fewer tokens, representing parallel approaches to cost optimization in AI inference
The Plunging Price of Thought Ember-1's 40% token reduction directly exemplifies the 'plunging price of thought' thesis — specialized efficiency-focused models are a key mechanism driving down inference costs

Related to

DeepSeek-V4.1-Flash: Smaller, Faster AI Model DeepSeek-V4.1-Flash and Ember-1 both represent the trend of smaller, more efficient models that match larger model quality — parallel releases pursuing the same efficiency-first design philosophy
SWE-2: Advanced Coding Model with Improved Cost-Capability Tradeoff Both SWE-2 and Ember-1 are positioned as models with improved cost-capability tradeoffs specifically for coding tasks, representing competing approaches in the efficiency-focused coding model space

Challenges

Tokens Too Cheap to Meter The 'tokens too cheap to meter' thesis is complicated by Ember-1's existence — the continued market emphasis on 40% token savings suggests token cost still matters significantly at scale, pushing back on the 'post-scarcity' framing

Type:	link
First published:	Monday, 28 September 2026 at 11:34 UTC
Location:	https://fireworks.ai/blog/ember-1
URL:	https://mattwood.fyi/i/9c50b3c2

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