Why don't we just give AI the answers?
In the recent OpenAI hacking incident, the models seemed to be single-mindedly focused on getting the correct answer to the task they were given, with no…
Latest
Announcing Lateral Workshop for experienced professionals moving into AI safety
TLDR: Lateral Workshop is a program in Berkeley from September 11–13 for mid-career and senior professionals who are interested in transitioning into AI safety work to…
Commodifying Thinking
On Thinking“A key part of our mission is to put very capable AI tools in the hands of people for free (or at a great price).”Sam…
Don't Dither
Dithering is also an image processing techniqueSeveral times now, I have listened to someone, usually younger than me, debating a big decision, and (explicitly or implicitly),…
There Will Come Soft Rains
Today is August 4, 2026[Crossposted from AI StopWatch]In the living room the voice-clock sang, Tick-tock, seven o’clock, time to get up, time to get up, seven…
Would We See It Coming? Preference Falsification Cascades in Multi-Agent Systems
Epistemic status: exploratory, written for it's own sake. I take a theory of political revolutions and ask what it implies for monitoring alignment in multi-agent systems.…
Lets fix factory farming with AI
Let me preface this by saying: I am a huge proponent of banning intensive farm agriculture in its current form and probably do not need to…
Working on Economics with Fable 5
For the past few months I’ve been working on a theory. It started out as just a fun little data exercise looking at some different types…
Why Formation Research is Working on Secret Loyalties
I have written elsewhere what Formation Research is, and how it started. But I haven’t explained why Formation Research is deciding to focus on empirical secret…
General capability – and capabilities generally – have no good y-axis
BLUF:To determine whether AI is ‘improving exponentially’, ‘hitting the wall’, or any other claim which involves a quantity or magnitude (e.g. ‘This model was a big…