OD
To Improve LLMs, Coach Them Like Athletes in an Arena
AI RESEARCH

To Improve LLMs, Coach Them Like Athletes in an Arena

Games will teach you more about model capabilities than benchmarks ever could

Alex Duffy avatarALEX DUFFY

Latest articles

Claude Code Q&A: What Works, What Doesn't, and What Will Save You Hours

SOURCE CODE

Vibe Check: Claude Sonnet 4 Now Has a 1-million Token Context Window

VIBE CHECK

Best of the Pod: Vercel's Guillermo Rauch on What Comes After Coding

PODCAST

Built by us

Try out our products.

Tensr

Tensr

Statistical analysis platform

Try it
Registry

Registry

Ownership records, claim-ready

Try it
Notik

Notik

Revision that sticks

Try it

Dispatches From the Frontiers of AI

The latest models, capabilities, products, and use cases.

Putting AI to Work

Everything you need to know about how to use LLMs.

Worth reading occasionally.

Notes on building, designing, and shipping — from a studio that does all three. Join founders and builders who want the real version.

TensrRegistryNotik

The Future of Programming

Build less. Code more.

Thesis

Big ideas from the smartest people in technology.

From our columnists

Dan Shipper

Dan Shipper is the CEO and cofounder of Every. Every week he explores the frontiers of AI in his column, Chain of Thought, and on his podcast, 'AI & I.'

Read more from Dan

Building something
and need more than a studio?

We co-build with early-stage founders — equity, sprints, or a technical co-founder. Selective; let's talk if it fits.

Tell us about it →