Text Compression Can Help Secure Model Weights
Associated Paper: link[1]Paper Co-authors: Roy Rinberg, Annabelle Michael Carrell, Simon Henniger, Nicholas Carlini, Keri WarrTwo…
Category: Opinion
A summary of Condensation and its relation to Natural Latents
Short summary of CondensationCondensation is a theory of concepts by Sam Eisenstat. The paper can…
Maybe there’s a pattern here?
1.It occurred to me that if I could invent a machine—a gun—which could by its…
Gemini 3.1 Pro Aces Benchmarks, I Suppose
I’ve been trying to find a slot for this one for a while. I am…
Gen Z and AI: Education, Well-being, and the Labour Market
SummaryGeneration Z (Gen Z) is widely considered the first cohort to come of age entirely…
Is GDP a Kind of Factory?
This is a heavily excerpted linkpost.In 2021, economists Arvind Subramanian, Justin Sandefur, and Dev Patel…
Make Powerful Machines Verifiable
When verification brings no significant risks, refusal is a confessionWhile the subtitle might echo the…
How a Pinky Promise once stopped a war in the Middle East.
Note: Thought this pearl of history might be refreshing to post here considering the current…
Split Personality Training can detect Alignment Faking
This research was initiated and led by Florian Dietz, with funding from Coefficient Giving (formerly…
Physics of RL: Toy scaling laws for the emergence of reward-seeking
TL;DR:When is or isn't reward the optimization target? I use a mathematical toy model to…