Benjamin Sturgeon

Inkhaven: 30 Days of Posts

A 30-day writing challenge at Lighthaven, exploring AI safety, politics, and positive futures.

How did the United States hand over its future to corporations?
The Physics of Great Storytelling
The Garden (Part 1)
The Garden (Complete)
Spectator Sport
How Does an Agent with Multiple Goals Choose a Target?
Spend Money to Buy Opportunity
Revisiting GSM-Symbolic: Do 2026 Frontier Models Still Fail at Confounded Grade School Math?
This Is Not Financial Advice
How South Africa's Electricity Catastrophe Was (Mostly) Fixed
How to Make a Problem Disappear
Is the Adult in the Room with Us Right Now?
Characterising the Views on Safety from Frontier AI Labs: Anthropic and DeepMind
Characterising the Views on Safety from Frontier AI Labs: OpenAI
A Case for Persona Robustness as a Research Area
You Can Just Build Things with Claude Code
Do Models Know They're Lying When Claiming Fake Identities?
Which Information Sources I Listen to the Most
People That Inspire Me
Contributing to Technical Research in the AI Safety End Game
Giving AI a Childhood
Whatever I Was Doing in 2020, I Should Do Again
Whatever I Was Doing in 2020, I Should Do Again (Continued)
Do Emergently Misaligned Models Believe What They Say?
The Great Smoothing Out
Why Are Anglophone Countries Unhappier Than Their European Counterparts?
From Output to Connection
Attachment Theory Is Extremely Cool and Useful
Q&A
Linkpost: Sanity-Checking 'Incompressible Knowledge Probes'