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.

Baseten: High-Performance AI Inference Platform

Connections

Supports

Town: Personalized AI Assistant Exits Beta with $55M Series A High-performance inference platforms like Baseten are the likely backbone enabling the low-latency responses required by personalized assistants such as Town.

Fireworks AI: Specialized Intelligence Infrastructure Fireworks AI and Baseten occupy the same market niche of specialized, high-performance inference platforms distinct from hyperscaler offerings.
Valkey: Open Source High-Performance Key/Value Datastore Valkey's high-performance key/value caching is a common infrastructure dependency for low-latency inference platforms like Baseten.
Open Athena Both address AI infrastructure access, with Open Athena representing an open-source counterpart to Baseten's managed inference offering.
Together AI: Research-Driven Inference and Training Platform Together AI and Baseten both compete on inference performance benchmarks and kernel-level optimization for serving models.
How Keras 3 Modernized Expedia's Lodging Ranking Stack Baseten's high-performance inference platform addresses similar enterprise ML infrastructure challenges that Expedia faced when upgrading their ranking stack with Keras 3

Challenged by

Databricks AI: Agent Bricks and Unity AI Gateway Databricks' agent-building tools compete with Baseten's inference infrastructure by offering an integrated alternative for deploying performant AI systems.
11–16× Faster LLM Inference with llama.cpp 11-16x faster local inference via llama.cpp on Apple Silicon GPU passthrough directly competes with high-performance cloud inference platforms like Baseten, making on-device inference more viable
AMD acquires AI chip startup Taalas to boost inference performance by etching models into silicon AMD's hardware-level inference optimization via Taalas directly challenges software-layer inference platforms like Baseten by potentially offering superior throughput at the silicon level

Supported by

Ways to think about token pricing Token price volatility and supply crunch dynamics justify Baseten's value proposition of delivering more performant, cost-efficient inference.

Type:	link
First published:	Monday, 20 July 2026 at 12:00 UTC
Location:	https://www.baseten.co/
URL:	https://mattwood.fyi/i/f5012f75

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