Inducing human-like biases in moral reasoning LMs

Um..! 13 posts in total. Keep on posting.

2024

02-27

Inducing human-like biases in moral reasoning LMs

02-02

How important is AI hacking as LLMs advance

2023

06-25

Third condition of the deceptive alignment

2022

10-20

About PAIS and Risks from Learned Optimization

09-05

ML Safety Scholars

2021

02-27

Intro to plain text productivity

2020

03-05

Sample ASP.NET Core Web API project

2019

05-22

Сытые философы или конкурентное программирование на .NET

2017

08-06

Code Complete, 2nd by Steve McConnell

07-21

Notes from "Architecting Applications for the Enterprise"