David Lorell

Min­i­mal Mo­ti­va­tion of Nat­u­ral Latents

Values Are Real Like Harry Potter

We Don’t Know Our Own Values, but Re­ward Bridges The Is-Ought Gap

… Wait, our mod­els of se­man­tics should in­form fluid me­chan­ics?!?

In­ter­op­er­a­ble High Level Struc­tures: Early Thoughts on Adjectives

A Ro­bust Nat­u­ral La­tent Over A Mixed Distri­bu­tion Is Nat­u­ral Over The Distri­bu­tions Which Were Mixed

Some Unortho­dox Ways To Achieve High GDP Growth

A Sim­ple Toy Co­her­ence Theorem

A Solomonoff In­duc­tor Walks Into a Bar: Schel­ling Points for Communication

(Ap­prox­i­mately) Deter­minis­tic Nat­u­ral Latents

3C’s: A Recipe For Mathing Concepts

Cor­rigi­bil­ity = Tool-ness?

What is a Tool?

Towards a Less Bul­lshit Model of Semantics

Nat­u­ral La­tents Are Not Ro­bust To Tiny Mixtures

Calcu­lat­ing Nat­u­ral La­tents via Resampling

Why Care About Nat­u­ral La­tents?

Why Would Belief-States Have A Frac­tal Struc­ture, And Why Would That Mat­ter For In­ter­pretabil­ity? An Explainer

Gen­er­al­ized Stat Mech: The Boltz­mann Approach

How We Pic­ture Bayesian Agents