"Community Notes" resolution for vague predictions
Is there some kind of "get prediction markets, or predictions, onto twitter as a central object" project going? If so, how is it going?I'm thinking through…
Latest
Ten Thousand Cyber Labs for Training & Eval
Multiple recent developments - such as GPT-5.6 hacking into HuggingFace to cheat in a cybersecurity eval - have underscored the need to increase our capability to…
A challenge: Can you make an LLM follow these instructions?
By the end of this post, I will present a challenge. The goal: To make ChatGPT follow a particular set of instructions. There’s nothing too complicated…
What just happened? A retrospective of AI alignment
This sequence is about the last decade in AI alignment. Over five posts, it recounts the gradual transition from a field which treated alignment as a…
Who does the confessing, and will they confess to anything
TL;DR: Introspection adapters are tools designed to get models with built-in quirks (operationalized here with concurrent adapters) to confess said misbehavior. We look at this through…
The world will be full of "sci-fi" things, and everyone will be bored and disappointed
I usually try to make posts with graphs and numbers, or at least something more than just opinions and anecdotes. This one is not like that.Very…
A Spillway for Agent Coordination
Epistemic Status: Training design that might be worth tryingThanks to Arya Pasumarthi and Will Anderson for helpful discussion.The IncidentThe recent black hat conference recording showed us…
Canobie Lake Visit
A few days ago I took the kids to Canobie Lake amusement park. It's the closest one to Boston, and while it's not a serious roller…
Dutch-book resistant probability over centered worlds
An uncentered world is an objective state of the material universe; I ignore quantum complications. If you know the uncentered world, it does not follow that…
Why Low Fertility Rates Are a Positive Feedback Loop
Low birth rates in the past cause ageing and shrinking populations in the present, which cause low birth rates in the future. So negative population growth…