What if AI Safety employees unionised?
American bald eagle caws angrily in the distanceWhoa whoa whoa, just hear me out. Unions aren’t usually a good answer for free-market loving libertarians, but one…
Latest
Gemma The Unstopping: a Behavioral Experiment
Following up on my previous experiment - studying Gemma's behavior on agentic tasks when given the number of steps left across the run - I endeavored…
Enough is Enough: Measuring Diminishing returns to benchmark size with Item Response Theory
This is a speedrun sort of project completed at the start of the Pivotal Fellowship with inspiration and mentorship from SecureBio. It will probably be largely…
How to Do a ""Safety-focused"" Vape Company
Note: I'm not actually building this, but I'm happy to see someone take up the task, ironically or otherwise.ForewordThis is possibly one of the most important…
Toy Models of Initialisation Effects on RL Dynamics
This is a follow-up to two posts Geodesic released last week on our current research direction. The code for generating the figures can be found at…
Why frontier labs are scaling-pilled
This is a crosspost from my substack.What would it take to make progress towards general intelligence, where general stands for any problem that might arise in…
Our response to Séb Krier on Plan A
This criticism of AI 2040: Plan A by Séb Krier unfortunately seriously mischaracterizes our proposal. It also mostly contains flat assertions, not real argumentation, and the…
Making Credible Deals With AI
If we end up with a weakly superhuman scheming AI, trading with it may reduce takeover risk: offer it things it values (donate to causes that…
A (Romanticised) Taxonomy of Thinkers
The dialecticianI crave contact and direct haptic feedback from the world, seeking it far beyond my nominal area of expertise. I engage passionately in discussions with…
Posting Some Prompts
I’ve seen a number of posts where people complaining about AI slop say that the author should have just posted the prompt.LLMs write fine enough if…